Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-12T11:29:29.566369Z
Paper Citation Record · LEDGER
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
As of 20 August 2026, this Paper Citation Record lists 100 of 151 outbound references and 11 inbound Pith citation observations for arXiv:2411.18191.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-16T04:39:33.863704Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-04T08:29:42.345373Z
Reference resolution
100 of 151 outbound references displayed
- verified exact2
- verified fuzzy0
- unresolved98
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation cc8e2454-5411-4ee6-b735-50654d827b3e · outbound
This paper cites https://github.com/ liuhuanyong/CrimeKgAssitant.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks https://github.com/ liuhuanyong/CrimeKgAssitant
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.256197Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 764a5297-dc91-4ce7-83ce-6b3b150bfb82 · outbound
This paper cites https://webutility.io/.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks https://webutility.io/
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.259512Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 27cf82f7-0f10-4169-aad9-fe1dd01e987e · outbound
This paper cites Prompt caching (beta).
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Prompt caching (beta)
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.262272Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9891a9d1-32c4-44ca-b1d8-cf29e7e89bce · outbound
This paper cites Tutorial: Use Azure Cache for Redis as a seman- tic cache.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Tutorial: Use Azure Cache for Redis as a seman- tic cache
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.264959Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b4958e14-cf02-4362-9c34-9388a08366db · outbound
This paper cites Qwen Technical Report.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Qwen Technical Report
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.268329Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 612434fa-56ec-498a-b26b-efdad6e0df3d · outbound
This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.271871Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fbed0cbf-4092-421d-ac00-ec3a433de680 · outbound
This paper cites Gptcache: An open-source semantic cache for llm appli- cations enabling faster answers and cost savings.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Gptcache: An open-source semantic cache for llm appli- cations enabling faster answers and cost savings
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.275578Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2f9bc8d4-2d50-4be8-94e9-6b7fdea869b1 · outbound
This paper cites {CSI}{NN}: Reverse engineering of neural network architectures through electromagnetic side channel.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks {CSI}{NN}: Reverse engineering of neural network architectures through electromagnetic side channel
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.278870Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ac6ddc2e-d090-490e-bd57-a2545c908209 · outbound
This paper cites A desynchronization-based countermeasure against side-channel anal- ysis of neural networks.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks A desynchronization-based countermeasure against side-channel anal- ysis of neural networks
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.281890Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8b4d783f-44c7-4308-9618-f33c7deafc01 · outbound
This paper cites What does it mean for a language model to preserve privacy? In Proceedings of the 2022 ACM conference on fairness, accountability, and transparency , pages 2280–2292, 2022.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks What does it mean for a language model to preserve privacy? In Proceedings of the 2022 ACM conference on fairness, accountability, and transparency , pages 2280–2292, 2022
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.285023Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 55feaffa-093a-4099-b320-e06afc782a02 · outbound
This paper cites Language models are few-shot learners.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Language models are few-shot learners
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.288088Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b6bc9da7-8132-4686-ad18-1c71ea50c69f · outbound
This paper cites Cross-data knowledge graph construc- tion for llm-enabled educational question-answering system: A case study at hcmut.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Cross-data knowledge graph construc- tion for llm-enabled educational question-answering system: A case study at hcmut
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.291054Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f975d790-9562-4f13-a1f8-b15d7296ec80 · outbound
This paper cites Quantifying Memorization Across Neural Language Models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Quantifying Memorization Across Neural Language Models
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.294216Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ddc8f084-5461-4fa8-a675-3543367b33f8 · outbound
This paper cites Extracting training data from large language models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Extracting training data from large language models
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.297490Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ba47bb10-47ff-43e8-9cfc-f4e686cfa5d6 · outbound
This paper cites Evoprompting: lan- guage models for code-level neural architecture search.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Evoprompting: lan- guage models for code-level neural architecture search
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.300445Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 442b1b10-e398-4435-a0cf-14cdc0b07a40 · outbound
This paper cites Text embedding inversion security for multilingual language models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Text embedding inversion security for multilingual language models
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.303326Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3413af0e-5abb-4f5a-b808-3bd86e79fbb5 · outbound
This paper cites PaLM: Scaling Language Modeling with Pathways.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks PaLM: Scaling Language Modeling with Pathways
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.306611Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 08453d27-ffc5-470d-8ee6-bdf013b8e8c5 · outbound
This paper cites A Better LLM Evaluator for Text Generation: The Impact of Prompt Output Sequencing and Optimization.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks A Better LLM Evaluator for Text Generation: The Impact of Prompt Output Sequencing and Optimization
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.310008Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c16245ec-b59f-47b3-a56c-86afe5e70425 · outbound
This paper cites Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.313579Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9728ba4e-4dcb-4acc-86a5-ddb0a052bf82 · outbound
This paper cites How continuous batching enables 23x throughput in llm inference while reducing p50 latency, 2023.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks How continuous batching enables 23x throughput in llm inference while reducing p50 latency, 2023
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.317052Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 886cb677-9a08-4a8a-9a13-3bb4ecff4dcf · outbound
This paper cites Privacy side channels in machine learning systems.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Privacy side channels in machine learning systems
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.320105Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e3a9d8b1-1675-431f-8a6b-776e26c84ede · outbound
This paper cites DeepSeek API Docs: DeepSeek API introduces Context Caching on Disk, cutting prices by an order of magnitude.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks DeepSeek API Docs: DeepSeek API introduces Context Caching on Disk, cutting prices by an order of magnitude
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.322592Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ae7746de-504e-4f3d-b638-770bb5b2ebbb · outbound
This paper cites DeepSeek API introduces Context Caching on Disk, cutting prices by an order of magnitude.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks DeepSeek API introduces Context Caching on Disk, cutting prices by an order of magnitude
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.325372Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8a6d631c-8da6-4fa7-81d7-cd2f41cb7418 · outbound
This paper cites an unresolved cited work.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Unresolved cited work
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.327955Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5bc91299-eb1f-40bb-84bc-8e1e4829f466 · outbound
This paper cites LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.330733Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 65d0b975-f99a-4c52-87f7-e9b73d167e13 · outbound
This paper cites Piloting Copilot, Codex, and StarCoder2: Hot Temperature, Cold Prompts, or Black Magic?.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Piloting Copilot, Codex, and StarCoder2: Hot Temperature, Cold Prompts, or Black Magic?
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.333258Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8f8edf33-6279-4e61-87bb-c8cb94c40b0d · outbound
This paper cites Floating-point multiplication timing attack on deep neural network.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Floating-point multiplication timing attack on deep neural network
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.335977Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e1c26979-def8-487e-93b5-e8de2d577094 · outbound
This paper cites Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.338559Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 21379c7e-1779-48e0-b631-7368d6f74ec8 · outbound
This paper cites The Llama 3 Herd of Models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks The Llama 3 Herd of Models
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.341251Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation af9195ba-8195-498b-86cd-6203011d6af6 · outbound
This paper cites Stealing Neural Networks via Timing Side Channels.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Stealing Neural Networks via Timing Side Channels
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.344261Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7dd98c73-4d18-4cfd-b55e-bbf0bdff6009 · outbound
This paper cites Spy in the gpu-box: Covert and side channel attacks on multi-gpu systems.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Spy in the gpu-box: Covert and side channel attacks on multi-gpu systems
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.347807Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2ee6c837-cda0-4509-ae04-ec39b245c961 · outbound
This paper cites Semantic caching.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Semantic caching
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.350894Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2d16d641-1373-4235-b5a9-0d616b9aff2a · outbound
This paper cites Llm- ensemble: Optimal large language model ensemble method for e- commerce product attribute value extraction.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Llm- ensemble: Optimal large language model ensemble method for e- commerce product attribute value extraction
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.353633Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 176a13c8-0901-415a-91e3-70d3ca975e9d · outbound
This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.356582Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b72b87d9-2418-44e7-8ca6-fb79f9ed8813 · outbound
This paper cites Making Pre-trained Language Models Better Few-shot Learners.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Making Pre-trained Language Models Better Few-shot Learners
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.359693Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9c9b697f-7ddf-46e7-b5fa-a655f200a01a · outbound
This paper cites Free AI Story Generator.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Free AI Story Generator
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.362947Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4871614e-a6b7-41ec-bd97-421d3ffd7b2f · outbound
This paper cites MeanCache: User-Centric Semantic Caching for LLM Web Services.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks MeanCache: User-Centric Semantic Caching for LLM Web Services
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.365993Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d97d3a88-0bc5-4643-b646-2b56f2259590 · outbound
This paper cites Prompt cache: Modular attention reuse for low-latency inference.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Prompt cache: Modular attention reuse for low-latency inference
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.369094Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation de6c52ee-e2eb-4ac6-907f-9592e71b94f5 · outbound
This paper cites Reverse-engineering deep neural networks using floating-point timing side-channels.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Reverse-engineering deep neural networks using floating-point timing side-channels
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.372676Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a039c0d1-0c4e-48f9-a794-2b8ca2966eeb · outbound
This paper cites Gemini API : Google AI for Developers.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Gemini API : Google AI for Developers
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.375842Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6b5382ef-381f-4f60-a3db-8a3c73344f62 · outbound
This paper cites Ppt: Pre- trained prompt tuning for few-shot learning.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Ppt: Pre- trained prompt tuning for few-shot learning
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.378843Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c3716496-c5a3-4cf3-bbea-2c235c7b5e2c · outbound
This paper cites Comave: Contrastive pre-training with multi-scale masking for attribute value extraction.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Comave: Contrastive pre-training with multi-scale masking for attribute value extraction
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.382356Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 73097c2e-7772-4ed8-962c-233593c88cbd · outbound
This paper cites LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.385611Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1cecf479-aeb4-4df5-8ada-3888cea9745a · outbound
This paper cites Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks
Reference 44
- Resolution
- verified exact
- local_arxiv, observed 2026-08-12T11:29:30.298272Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 325b7e6b-225c-443c-bab7-1cb8463bf97c · outbound
This paper cites BarraCUDA: Edge GPUs do Leak DNN Weights.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks BarraCUDA: Edge GPUs do Leak DNN Weights
Reference 45
- Resolution
- verified exact
- local_arxiv, observed 2026-08-12T11:29:30.282800Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 43233a54-bbc7-4336-ac62-51bdc845270b · outbound
This paper cites Deepsniffer: A dnn model extraction framework based on learning architectural hints.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Deepsniffer: A dnn model extraction framework based on learning architectural hints
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.395444Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 756176a7-4980-47cd-9151-32e0f13fae9c · outbound
This paper cites Reverse engineer- ing convolutional neural networks through side-channel information leaks.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Reverse engineer- ing convolutional neural networks through side-channel information leaks
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.398843Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6d9b65af-3c80-47b5-8b9f-70291ca940c4 · outbound
This paper cites Are Large Pre-Trained Language Models Leaking Your Personal Information?.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Are Large Pre-Trained Language Models Leaking Your Personal Information?
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.402000Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b4d7fc81-8d7d-4195-91e6-e61400af3f41 · outbound
This paper cites Large Language Model Text Generation Inference.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Large Language Model Text Generation Inference
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.405231Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e6cb3f06-680d-4412-abc4-9984a28a85a1 · outbound
This paper cites How to better configure your cache; GPTCache.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks How to better configure your cache; GPTCache
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.408339Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e08b75aa-d22f-48be-942e-70a9afc68954 · outbound
This paper cites LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks LMDeploy is a toolkit for compressing, deploying, and serving LLMs
Reference 51
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.411013Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2ede56fe-fbb9-46d5-be44-a6eff4742be9 · outbound
This paper cites Hydragen: High-Throughput LLM Inference with Shared Prefixes.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Hydragen: High-Throughput LLM Inference with Shared Prefixes
Reference 52
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.414161Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bf3fb357-6b67-46bf-a792-c4472e18d132 · outbound
This paper cites HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications
Reference 53
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.416916Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e4d5e713-da4b-4832-a7e0-23c233f63968 · outbound
This paper cites Improve speed and reduce cost for generative AI workloads with a persistent semantic cache in Amazon MemoryDB.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Improve speed and reduce cost for generative AI workloads with a persistent semantic cache in Amazon MemoryDB
Reference 54
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.419591Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b31db8b0-97e7-4dfd-aff1-bbd42f924e9e · outbound
This paper cites Propile: Probing privacy leakage in large language models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Propile: Probing privacy leakage in large language models
Reference 55
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.422320Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dd502915-839d-48ce-be3e-46009e248109 · outbound
This paper cites Efficient memory management for large language model serving with pagedattention.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Efficient memory management for large language model serving with pagedattention
Reference 56
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.425299Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 37fcec31-ba01-48e2-848d-39f4cac1b8c9 · outbound
This paper cites Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?
Reference 57
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.428886Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f0141a56-2883-4d5e-b983-4b19fbdb3a09 · outbound
This paper cites Retrieval-augmented gen- eration for knowledge-intensive nlp tasks.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Retrieval-augmented gen- eration for knowledge-intensive nlp tasks
Reference 58
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.432301Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8056bf8a-80dc-4c01-9dc8-5de710449bb6 · outbound
This paper cites Sentence embedding leaks more information than you expect: Generative embedding inversion attack to recover the whole sentence.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Sentence embedding leaks more information than you expect: Generative embedding inversion attack to recover the whole sentence
Reference 59
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.435542Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3aa60a7e-3fc1-4aaa-b115-4bf2aed1762b · outbound
This paper cites Structured chain-of-thought prompting for code generation.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Structured chain-of-thought prompting for code generation
Reference 60
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.438943Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f8d75daa-a506-4acb-a31b-4c0236742279 · outbound
This paper cites SCALM: Towards Semantic Caching for Automated Chat Services with Large Language Models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks SCALM: Towards Semantic Caching for Automated Chat Services with Large Language Models
Reference 61
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.442085Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ef28f3bf-5b76-47f4-b8d9-b807623a9437 · outbound
This paper cites Chatdoctor: A medical chat model fine-tuned on a large language model meta-ai (llama) using medical domain knowledge.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Chatdoctor: A medical chat model fine-tuned on a large language model meta-ai (llama) using medical domain knowledge
Reference 62
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.445304Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 23d8d743-1235-45d2-a4a5-8999e92cd2be · outbound
This paper cites Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models
Reference 63
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.448706Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f90952c6-2621-4705-87b3-e0438296ee75 · outbound
This paper cites Student interaction with newtbot: An llm-as-tutor chatbot for secondary physics education.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Student interaction with newtbot: An llm-as-tutor chatbot for secondary physics education
Reference 64
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.452195Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b949ff28-878d-4570-9e6b-ac4dee632261 · outbound
This paper cites Awq: Activation-aware weight quantization for on-device llm compression and acceleration.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Awq: Activation-aware weight quantization for on-device llm compression and acceleration
Reference 65
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.455296Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 116628bc-64dc-4392-aba4-ef2843dd0161 · outbound
This paper cites Analyzing leakage of personally identifiable information in language models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Analyzing leakage of personally identifiable information in language models
Reference 66
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.458521Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 00de7e29-8a01-48e1-8f0b-712a761d43e7 · outbound
This paper cites Prompting hard or hardly prompting: Prompt inversion for text-to-image diffusion models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Prompting hard or hardly prompting: Prompt inversion for text-to-image diffusion models
Reference 67
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.461700Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ddf1c19f-0eeb-40d7-bfb9-b8530ae78cf1 · outbound
This paper cites Prompting hard or hardly prompting: Prompt inversion for text-to-image diffusion models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Prompting hard or hardly prompting: Prompt inversion for text-to-image diffusion models
Reference 68
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.465076Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 73828736-4dc0-487a-929d-c1bc272ee0e8 · outbound
This paper cites Leaky nets: Recovering embedded neural network models and inputs through simple power and timing side-channels—attacks and de- fenses.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Leaky nets: Recovering embedded neural network models and inputs through simple power and timing side-channels—attacks and de- fenses
Reference 69
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.468123Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2ff189a9-581b-4202-a308-f95a94cdb2fb · outbound
This paper cites Prompt engineering in large language mod- els.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Prompt engineering in large language mod- els
Reference 70
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.471647Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 479737e6-6708-429f-a9a3-0e08e0410caf · outbound
This paper cites Mem- bership inference attacks against language models via neighbour- hood comparison.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Mem- bership inference attacks against language models via neighbour- hood comparison
Reference 71
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.475196Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 76a22f53-0031-4fcf-8bae-88ea94a059a2 · outbound
This paper cites Did the neurons read your book? document-level membership inference for large language models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Did the neurons read your book? document-level membership inference for large language models
Reference 72
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.477773Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 937165e8-3829-4dba-8895-2a0ee1bdd6f9 · outbound
This paper cites Large language models challenge the future of higher education.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Large language models challenge the future of higher education
Reference 73
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.480276Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 18e12602-693a-42e9-8630-450b55c29488 · outbound
This paper cites Memorization in NLP Fine-tuning Methods.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Memorization in NLP Fine-tuning Methods
Reference 74
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.482742Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 71a43d59-4f47-4478-9eea-957067c95bde · outbound
This paper cites An empirical analy- sis of memorization in fine-tuned autoregressive language models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks An empirical analy- sis of memorization in fine-tuned autoregressive language models
Reference 75
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.485683Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2ddfca7d-1803-4ce8-9c96-638cc624d403 · outbound
This paper cites Context-based semantic caching for llm applications.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Context-based semantic caching for llm applications
Reference 76
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.488439Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9f204777-0a09-4b65-8fe0-ee52e2e0d1b9 · outbound
This paper cites Using the Context Caching Feature of the Kimi API.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Using the Context Caching Feature of the Kimi API
Reference 77
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.491328Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 45b786a2-c725-4131-8e9b-2786765fe9cb · outbound
This paper cites Language Model Inversion.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Language Model Inversion
Reference 78
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.494190Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6fc5ce6f-9730-484c-bad1-f2dd1b35f12c · outbound
This paper cites Text embeddings reveal (almost) as much as text.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Text embeddings reveal (almost) as much as text
Reference 79
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.497935Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0ce3f5a1-5e09-40b4-883c-9247b2e7f25e · outbound
This paper cites Rendered insecure: Gpu side channel attacks are practical.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Rendered insecure: Gpu side channel attacks are practical
Reference 80
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.500935Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 53218a10-dab8-4498-8ac9-dc788ceafdb0 · outbound
This paper cites SFR-RAG: Towards Contextually Faithful LLMs.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks SFR-RAG: Towards Contextually Faithful LLMs
Reference 81
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.504130Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d117dba2-a34f-4155-bffd-4b36edfd1e79 · outbound
This paper cites NVIDIA TensorRT-LLM.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks NVIDIA TensorRT-LLM
Reference 82
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.507437Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c46353e8-05d0-4522-a69a-6affd07a4508 · outbound
This paper cites Ragged Batching; NVIDIA Triton Inference Server.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Ragged Batching; NVIDIA Triton Inference Server
Reference 83
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.510510Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 25b8d5ac-5fbb-4379-b9c4-7e47eff9dc94 · outbound
This paper cites Gpt-4 turbo in the openai api.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Gpt-4 turbo in the openai api
Reference 84
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.513482Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a89865c7-00c9-4a4a-8e0e-d35cefce8bcc · outbound
This paper cites Openai developer platform, Rate limits.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Openai developer platform, Rate limits
Reference 85
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.516604Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e26a672b-4854-4e99-bf3e-544e7b20680f · outbound
This paper cites Introducing chatgpt.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Introducing chatgpt
Reference 86
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.519732Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 794d2e68-5bea-443f-b3d7-3c383f12a657 · outbound
This paper cites Introducing the GPT Store We’re launching the GPT Store to help you find.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Introducing the GPT Store We’re launching the GPT Store to help you find
Reference 87
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.522919Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1d929234-7e90-4653-a5ee-9080aaa335a6 · outbound
This paper cites Learning to Reason with LLMs We are introducing OpenAI o1, a new large language model trained with LLMs.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Learning to Reason with LLMs We are introducing OpenAI o1, a new large language model trained with LLMs
Reference 88
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.526339Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e1395945-3e12-4565-9d29-61873855c201 · outbound
This paper cites Prompt caching: Reduce latency and cost with prompt caching.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Prompt caching: Reduce latency and cost with prompt caching
Reference 89
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.529841Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b6179287-a5fa-4a27-99e3-a50952103bc1 · outbound
This paper cites Training language models to follow in- structions with human feedback.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Training language models to follow in- structions with human feedback
Reference 90
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.534440Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c6bcb5e3-b3f5-4923-b5d6-9c688a18c795 · outbound
This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Ignore Previous Prompt: Attack Techniques For Language Models
Reference 91
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.537644Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6fc34702-5ba3-462d-88fe-919a740d156d · outbound
This paper cites Efficiently scaling transformer inference.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Efficiently scaling transformer inference
Reference 92
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.541516Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8fc4c8ec-b986-4505-9030-3540bf81a270 · outbound
This paper cites Cache (Simple & Semantic) - Portkey Docs.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Cache (Simple & Semantic) - Portkey Docs
Reference 93
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.544492Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ff2ab8de-2c5e-46d0-8c67-433a6afb165e · outbound
This paper cites A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications
Reference 94
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.547816Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dfe424a7-671b-4a0f-9c7a-98c816364a8d · outbound
This paper cites Chatgpt utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Chatgpt utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns
Reference 95
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.551341Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3cd638b4-c102-494e-97bc-47d81fd50750 · outbound
This paper cites Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
Reference 96
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.554565Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d1b9846c-d8fa-4f1a-ae87-d401f2b80e66 · outbound
This paper cites Prompt Stealing Attacks Against Large Language Models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Prompt Stealing Attacks Against Large Language Models
Reference 97
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.558393Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 556b9e89-760c-4b1f-88c2-d0f5d3f75b83 · outbound
This paper cites Implementing Semantic Caching: A Step- by-Step Guide to Faster, Cost-Effective GenAI Workflows.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Implementing Semantic Caching: A Step- by-Step Guide to Faster, Cost-Effective GenAI Workflows
Reference 98
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.561070Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d226b00a-d56e-4a26-a353-8946e90f6bd6 · outbound
This paper cites OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Reference 99
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.563691Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2dab9e97-8355-443c-b44c-60d71495e9ac · outbound
This paper cites Prompting large language models with answer heuristics for knowledge-based visual question answering.
InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks Prompting large language models with answer heuristics for knowledge-based visual question answering
Reference 100
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T11:29:29.566369Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation 2b9a18fe-7249-460e-9c44-2ea442555e91 · inbound
Auditing Prompt Caching in Language Model APIs cites this paper.
Auditing Prompt Caching in Language Model APIs InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-08T11:39:40.833245Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4cd257bb-cd68-4277-9cf5-e73d774093e6 · inbound
Spill The Beans: Exploiting CPU Cache Side-Channels to Leak Tokens from Large Language Models cites this paper.
Spill The Beans: Exploiting CPU Cache Side-Channels to Leak Tokens from Large Language Models InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-16T04:39:33.863704Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 070e7746-2e06-48d8-9efd-423014f82c84 · inbound
SoK: Semantic Privacy in Large Language Models cites this paper.
SoK: Semantic Privacy in Large Language Models InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T21:40:35.933082Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6aa74733-1d0f-4758-9173-10629f5ad937 · inbound
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching cites this paper.
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:17:23.323689Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2356cd12-4851-4ead-9026-bd3dc32825dd · inbound
Security Considerations for Multi-agent Systems cites this paper.
Security Considerations for Multi-agent Systems InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
Reference 277
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T14:15:55.789620Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation dbf315d7-dfbd-4f9e-b577-262e76188159 · inbound
PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems cites this paper.
PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
Reference 76
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T12:15:06.748430Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 698b1973-37d7-4b42-b6a7-f5812744baa2 · inbound
CachePrune: Privacy-Aware and Fine-Grained KV Cache Sharing for Efficient LLM Inference cites this paper.
CachePrune: Privacy-Aware and Fine-Grained KV Cache Sharing for Efficient LLM Inference InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
Reference 68
- Resolution
- verified exact
- arxiv_id, observed 2026-05-25T04:15:19.795495Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation fd28c7a6-a89e-40b9-8748-469a416a54e0 · inbound
Investigating The Security of Modern AI and Cloud Infrastructure cites this paper.
Investigating The Security of Modern AI and Cloud Infrastructure InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
Reference 151
- Resolution
- verified exact
- arxiv_id, observed 2026-07-04T08:29:42.347000Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 1161d847-04c4-4f65-a65e-089ade15f53a · inbound
Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing cites this paper.
Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
Reference 74
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T09:36:02.185670Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0bc2f1d1-4098-4c58-a31b-0b9f854ec8c3 · inbound
SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels cites this paper.
SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
Reference 100
- Resolution
- unresolved
- no resolver link, observed 2026-08-08T04:21:30.504440Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1b79cd63-22fa-4a80-a38b-5a4ad1fa6c50 · inbound
Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference cites this paper.
Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T14:30:48.401787Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.