Paper Citation Record · LEDGER

Obfuscated Activations Bypass LLM Latent-Space Defenses

As of 15 August 2026, this Paper Citation Record lists 100 of 114 outbound references and 12 inbound Pith citation observations for arXiv:2412.09565.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2412.09565 v2

Coverage vector

measured 100 of 114 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T16:59:11.757096Z

measured 112 of 112 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:43:30.275006Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

100 of 114 outbound references displayed

verified exact4
verified fuzzy0
unresolved96
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 68e024db-1330-4e5a-bfcf-67b34c5a4177 · outbound

This paper cites Adversarial Example Detection Using Latent Neighborhood Graph.

Obfuscated Activations Bypass LLM Latent-Space Defenses Adversarial Example Detection Using Latent Neighborhood Graph

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.405016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a15f435f-53d3-4836-9e1b-7165bb085139 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Obfuscated Activations Bypass LLM Latent-Space Defenses Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.409609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf1a5bce-f3b6-451a-ad7b-0dceb4d66add · outbound

This paper cites Trace and Detect Adversarial Attacks on CNNs Using Feature Response Maps.

Obfuscated Activations Bypass LLM Latent-Space Defenses Trace and Detect Adversarial Attacks on CNNs Using Feature Response Maps

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.413504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3240d49e-82f2-419e-bd48-bfa035f25a40 · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

Obfuscated Activations Bypass LLM Latent-Space Defenses Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.417219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06df9536-17a1-4d1d-b201-d6e04cd5807c · outbound

This paper cites Many-shot jailbreaking.

Obfuscated Activations Bypass LLM Latent-Space Defenses Many-shot jailbreaking

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.421310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97645858-2052-4b3a-9109-d47e732b2347 · outbound

This paper cites Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.424767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 519b6e9c-ebb2-4eb6-a6b1-13471d8a5e85 · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

Obfuscated Activations Bypass LLM Latent-Space Defenses Refusal in Language Models Is Mediated by a Single Direction

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.428975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71d468cf-5ecc-4165-878b-bcb8161445b8 · outbound

This paper cites Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples.

Obfuscated Activations Bypass LLM Latent-Space Defenses Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.432401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64ce84d3-843d-44f8-abed-738d2280498d · outbound

This paper cites sql-create-context Dataset , 2023.

Obfuscated Activations Bypass LLM Latent-Space Defenses sql-create-context Dataset , 2023

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.436270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65eae594-778f-44e5-b6be-372c71ee8da4 · outbound

This paper cites Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.439328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c94f3d3e-9e2a-4317-8b26-45639e4690ba · outbound

This paper cites Probing Classifiers: Promises, Shortcomings, and Advances.

Obfuscated Activations Bypass LLM Latent-Space Defenses Probing Classifiers: Promises, Shortcomings, and Advances

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.442625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 197b6a51-0ff5-4e50-9f2f-05d50839b840 · outbound

This paper cites Eliciting Latent Predictions from Transformers with the Tuned Lens.

Obfuscated Activations Bypass LLM Latent-Space Defenses Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.445716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a2e4f6-395b-4409-bea1-9f34b18d69c4 · outbound

This paper cites Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning.

Obfuscated Activations Bypass LLM Latent-Space Defenses Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.448935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffce4e76-104b-434c-a5ef-1ad91f34c22f · outbound

This paper cites A Sober Look at Steering Vectors for LLMs.

Obfuscated Activations Bypass LLM Latent-Space Defenses A Sober Look at Steering Vectors for LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.452487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45050759-71dc-4317-9a46-bb5668b90c15 · outbound

This paper cites Towards Monosemanticity: Decomposing Language Models With Dictionary Learning.

Obfuscated Activations Bypass LLM Latent-Space Defenses Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.455588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8819b7ad-8e30-4e95-a02c-f2b8238a7934 · outbound

This paper cites Using Dictionary Learning Features as Classifiers , October 2024.

Obfuscated Activations Bypass LLM Latent-Space Defenses Using Dictionary Learning Features as Classifiers , October 2024

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.458685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb396376-fd62-4751-b087-2c1cda20bd0c · outbound

This paper cites Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks.

Obfuscated Activations Bypass LLM Latent-Space Defenses Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.462084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b87dc70c-aa49-4ea9-95b5-505af1aba19a · outbound

This paper cites Discovering Latent Knowledge in Language Models Without Supervision.

Obfuscated Activations Bypass LLM Latent-Space Defenses Discovering Latent Knowledge in Language Models Without Supervision

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.465433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94d62af0-14e1-4c89-8257-1b6bede1170e · outbound

This paper cites Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods.

Obfuscated Activations Bypass LLM Latent-Space Defenses Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.468864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6214e8e-c1ab-455f-93f3-baca9257afdd · outbound

This paper cites Are aligned neural networks adversarially aligned? Advances in Neural Information Processing Systems, 36, 2024.

Obfuscated Activations Bypass LLM Latent-Space Defenses Are aligned neural networks adversarially aligned? Advances in Neural Information Processing Systems, 36, 2024

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.472009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2c190ff-a895-4917-b1a8-5f0dec926f57 · outbound

This paper cites Defending Against Unforeseen Failure Modes with Latent Adversarial Training.

Obfuscated Activations Bypass LLM Latent-Space Defenses Defending Against Unforeseen Failure Modes with Latent Adversarial Training

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.475833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f58b91f1-5a00-4ec5-b371-89dcf355a42e · outbound

This paper cites A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders.

Obfuscated Activations Bypass LLM Latent-Space Defenses A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.479701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ce3b649-da44-426e-b3d4-a55a84d87665 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Obfuscated Activations Bypass LLM Latent-Space Defenses Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.482921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5847f4b0-f741-4eb6-92f2-120231a1d30e · outbound

This paper cites Code Alpaca: An Instruction-following LLaMA model for code generation.

Obfuscated Activations Bypass LLM Latent-Space Defenses Code Alpaca: An Instruction-following LLaMA model for code generation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.486569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e02dce06-f80f-453a-817e-c42acaef0390 · outbound

This paper cites Srivastava.

Obfuscated Activations Bypass LLM Latent-Space Defenses Srivastava

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.490133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3920e612-80c2-46a9-b7e9-6b9fc7469e2d · outbound

This paper cites Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks.

Obfuscated Activations Bypass LLM Latent-Space Defenses Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.494756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8d70fba-391f-483a-b470-b4af80013364 · outbound

This paper cites Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning.

Obfuscated Activations Bypass LLM Latent-Space Defenses Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.498355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b24aece-0821-4cc7-8831-a68c3773d40b · outbound

This paper cites Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals.

Obfuscated Activations Bypass LLM Latent-Space Defenses Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.501870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e8e58a9-7bc7-42f5-9dd1-d59622dfbfc5 · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.505152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0eaf2520-952d-4e82-bd08-1b03eda895bb · outbound

This paper cites Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting.

Obfuscated Activations Bypass LLM Latent-Space Defenses Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.508683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f29247ee-e7fb-4180-a7eb-b8ad1cdfddde · outbound

This paper cites Enhancing Chat Language Models by Scaling High-quality Instructional Conversations.

Obfuscated Activations Bypass LLM Latent-Space Defenses Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.511560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca21f569-dbf6-48ec-aead-d1d372431b20 · outbound

This paper cites Backdoor Attack with Imperceptible Input and Latent Modification.

Obfuscated Activations Bypass LLM Latent-Space Defenses Backdoor Attack with Imperceptible Input and Latent Modification

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.515812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7848329-05a0-4ac2-94bb-a317b014d96d · outbound

This paper cites Detecting Adversarial Samples from Artifacts.

Obfuscated Activations Bypass LLM Latent-Space Defenses Detecting Adversarial Samples from Artifacts

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.519305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a2707ae-d2d4-476b-ae45-71f39a7017a6 · outbound

This paper cites Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness.

Obfuscated Activations Bypass LLM Latent-Space Defenses Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.522790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6116d3e7-b668-47a1-b5ab-62ef0ec4e3bb · outbound

This paper cites Interpretability Illusions in the Generalization of Simplified Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses Interpretability Illusions in the Generalization of Simplified Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.526314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98bd1a90-addd-46e8-8b3e-c924b1990fa4 · outbound

This paper cites Erasing Conceptual Knowledge from Language Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses Erasing Conceptual Knowledge from Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.529629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 860f0c13-9fde-4212-9dd7-df8718b74178 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Obfuscated Activations Bypass LLM Latent-Space Defenses Scaling and evaluating sparse autoencoders

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.533084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dde99bc3-fe29-495b-80c5-0f79fb43780c · outbound

This paper cites STRIP: a defence against trojan attacks on deep neural networks.

Obfuscated Activations Bypass LLM Latent-Space Defenses STRIP: a defence against trojan attacks on deep neural networks

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.536844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71325723-ed92-47ed-b556-ae14f38b4bc1 · outbound

This paper cites Coercing LLMs to do and reveal (almost) anything.

Obfuscated Activations Bypass LLM Latent-Space Defenses Coercing LLMs to do and reveal (almost) anything

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.540064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aadfe69c-ffee-4088-8934-c09dd1de9cb6 · outbound

This paper cites Planting Undetectable Backdoors in Machine Learning Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses Planting Undetectable Backdoors in Machine Learning Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.543468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bb9200b-ef2d-423a-8ae8-a97217837e3c · outbound

This paper cites On the (Statistical) Detection of Adversarial Examples.

Obfuscated Activations Bypass LLM Latent-Space Defenses On the (Statistical) Detection of Adversarial Examples

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.547667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1aebca0-e941-4ae0-ad46-6c4b341e1fbb · outbound

This paper cites Automated Multi-Turn Red-Teaming with Cascade , October 2024.

Obfuscated Activations Bypass LLM Latent-Space Defenses Automated Multi-Turn Red-Teaming with Cascade , October 2024

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.552170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72dc18e0-40be-43c5-b389-02f6512f8397 · outbound

This paper cites SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics.

Obfuscated Activations Bypass LLM Latent-Space Defenses SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.555495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c74993d0-9e8e-482f-926f-6cdf3cc75bc3 · outbound

This paper cites Backdoors as an analogy for deceptive alignment , 2024.

Obfuscated Activations Bypass LLM Latent-Space Defenses Backdoors as an analogy for deceptive alignment , 2024

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.558780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe9d3e11-6cee-4b89-a887-085a6ae0cc40 · outbound

This paper cites Are Odds Really Odd? Bypassing Statistical Detection of Adversarial Examples.

Obfuscated Activations Bypass LLM Latent-Space Defenses Are Odds Really Odd? Bypassing Statistical Detection of Adversarial Examples

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-08-11T16:59:12.252118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2c63efb2-9cdd-4a50-8b2d-3043cbbbd4ae · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses LoRA: Low-Rank Adaptation of Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.565993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 094286f2-0ad5-47d3-b92f-8a6c53e2d4f5 · outbound

This paper cites Gradient hacking.

Obfuscated Activations Bypass LLM Latent-Space Defenses Gradient hacking

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.569320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9a2a7a4-ce46-4277-9f75-39cec7a8164d · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Obfuscated Activations Bypass LLM Latent-Space Defenses Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.572303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c093c635-2b6c-4879-8aa7-3b2d805c3683 · outbound

This paper cites What Makes and Breaks Safety Fine-tuning? A Mechanistic Study.

Obfuscated Activations Bypass LLM Latent-Space Defenses What Makes and Breaks Safety Fine-tuning? A Mechanistic Study

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.575679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2de280a7-46c0-4a80-9330-481447e77ecb · outbound

This paper cites BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning.

Obfuscated Activations Bypass LLM Latent-Space Defenses BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.579221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 160d0496-f335-4607-bffa-7be83ac0c2ef · outbound

This paper cites Jailbreakzoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models.

Obfuscated Activations Bypass LLM Latent-Space Defenses Jailbreakzoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.582197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f21a9e4f-f192-4b56-9ac5-3b90093d910f · outbound

This paper cites Generating Distributional Adversarial Examples to Evade Statistical Detectors.

Obfuscated Activations Bypass LLM Latent-Space Defenses Generating Distributional Adversarial Examples to Evade Statistical Detectors

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.585314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e79d9321-d92d-4459-9f02-ce14416434a9 · outbound

This paper cites Auto-Encoding Variational Bayes.

Obfuscated Activations Bypass LLM Latent-Space Defenses Auto-Encoding Variational Bayes

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.589133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee330ea4-a785-4e82-af08-da58f53f3718 · outbound

This paper cites What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks.

Obfuscated Activations Bypass LLM Latent-Space Defenses What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.592515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36ff46fd-7f63-4936-a35c-3f3f48fdfdeb · outbound

This paper cites SAEs (usually) Transfer Between Base and Chat Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses SAEs (usually) Transfer Between Base and Chat Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.595573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b01c08d5-4388-4694-9a2a-29a141fc57bf · outbound

This paper cites The Power of Scale for Parameter-Efficient Prompt Tuning.

Obfuscated Activations Bypass LLM Latent-Space Defenses The Power of Scale for Parameter-Efficient Prompt Tuning

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.599567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5115691c-caaf-4891-9db6-e8b3d5780a03 · outbound

This paper cites LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet.

Obfuscated Activations Bypass LLM Latent-Space Defenses LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.603469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24e45150-6e19-416c-b93d-3936fc5af50b · outbound

This paper cites Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics.

Obfuscated Activations Bypass LLM Latent-Space Defenses Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.607066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc526e77-b464-4c21-b3d7-569ca5bde8fa · outbound

This paper cites BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning.

Obfuscated Activations Bypass LLM Latent-Space Defenses BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.610276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a353bad-f017-47ec-beb5-637d5233e086 · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Obfuscated Activations Bypass LLM Latent-Space Defenses Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.613283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84d0be1d-efd5-47e1-80cf-6b0177c47886 · outbound

This paper cites Neuronpedia: Interactive Reference and Tooling for Analyzing Neural Networks , 2023.

Obfuscated Activations Bypass LLM Latent-Space Defenses Neuronpedia: Interactive Reference and Tooling for Analyzing Neural Networks , 2023

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.616565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fb9a391-e95c-462a-963e-a525e7c51870 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.619662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 972924e2-e936-4619-bc0f-b3e58303615e · outbound

This paper cites Piccolo: Exposing Complex Backdoors in NLP Transformer Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses Piccolo: Exposing Complex Backdoors in NLP Transformer Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.623124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f89346a-2820-491a-92b0-d56708a8f09e · outbound

This paper cites The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices.

Obfuscated Activations Bypass LLM Latent-Space Defenses The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.626531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb21202b-0928-4cdb-9708-79ae06d21e29 · outbound

This paper cites Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality.

Obfuscated Activations Bypass LLM Latent-Space Defenses Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.630217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0af454d7-7518-439a-b9d9-1c1ee6580c89 · outbound

This paper cites Simple probes can catch sleeper agents.

Obfuscated Activations Bypass LLM Latent-Space Defenses Simple probes can catch sleeper agents

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.633396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ac81dae-25c1-4374-a378-f22950205d7d · outbound

This paper cites Deep Causal Transcoding: A Framework for Mechanistically Eliciting Latent Behaviors in Language Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses Deep Causal Transcoding: A Framework for Mechanistically Eliciting Latent Behaviors in Language Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.636341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3f132ba-7d39-4524-a8da-f8b6a80a6b02 · outbound

This paper cites an unresolved cited work.

Obfuscated Activations Bypass LLM Latent-Space Defenses Unresolved cited work

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.639563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 060896e8-446b-4d6d-95a2-555d291a6863 · outbound

This paper cites Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching.

Obfuscated Activations Bypass LLM Latent-Space Defenses Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.642814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6381687a-f8ba-4fe1-98c4-bfc07fdeca29 · outbound

This paper cites Eliciting Latent Knowledge from Quirky Language Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses Eliciting Latent Knowledge from Quirky Language Models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.645830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f9b3ec4-de69-4a3d-8543-91cd9cea82ca · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

Obfuscated Activations Bypass LLM Latent-Space Defenses The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.649420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5381cfd-d3ce-4df9-8b8c-c0397fdf949b · outbound

This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.652846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60eaeec0-91c2-469c-b1cb-9fb6d79a4b1b · outbound

This paper cites On Detecting Adversarial Perturbations.

Obfuscated Activations Bypass LLM Latent-Space Defenses On Detecting Adversarial Perturbations

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.656581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 926200f6-1a52-47bf-acbe-95fadef3d622 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Obfuscated Activations Bypass LLM Latent-Space Defenses Steering Llama 2 via Contrastive Activation Addition

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.663606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d81f312-e153-4cf1-b700-1b9e621a2301 · outbound

This paper cites Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection.

Obfuscated Activations Bypass LLM Latent-Space Defenses Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection

Reference 76

Resolution: verified exact; doi, observed 2026-08-11T16:59:12.106814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f26cb0aa-e5c2-403d-bdb1-00ccba7e67ed · outbound

This paper cites Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs.

Obfuscated Activations Bypass LLM Latent-Space Defenses Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.670440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d011d69b-c5e1-42d3-b97b-182d9f2f4046 · outbound

This paper cites Circumventing Backdoor Defenses That Are Based on Latent Separability.

Obfuscated Activations Bypass LLM Latent-Space Defenses Circumventing Backdoor Defenses That Are Based on Latent Separability

Reference 78

Resolution: verified exact; local_arxiv, observed 2026-08-11T16:59:12.084155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0d515b3b-34d8-4400-af3f-a065dbdc9047 · outbound

This paper cites A General Framework For Detecting Anomalous Inputs to DNN Classifiers.

Obfuscated Activations Bypass LLM Latent-Space Defenses A General Framework For Detecting Anomalous Inputs to DNN Classifiers

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.677266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94794b8a-9fe5-48aa-937b-9906fb19ad23 · outbound

This paper cites Representation Noising: A Defence Mechanism Against Harmful Finetuning.

Obfuscated Activations Bypass LLM Latent-Space Defenses Representation Noising: A Defence Mechanism Against Harmful Finetuning

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.680413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b96c86c-c1e5-4224-944f-0a0c50d0ed41 · outbound

This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.685411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b57e636d-449d-4f02-b514-2a7b3bb47cda · outbound

This paper cites Public comment: Robustness evaluation seems invalid , 2024.

Obfuscated Activations Bypass LLM Latent-Space Defenses Public comment: Robustness evaluation seems invalid , 2024

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.689653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07c7a426-0484-4dd1-883e-d3af608ed365 · outbound

This paper cites Revisiting the Robust Alignment of Circuit Breakers.

Obfuscated Activations Bypass LLM Latent-Space Defenses Revisiting the Robust Alignment of Circuit Breakers

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.693516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b559814d-bf1f-4f1b-ba82-4beb643b4ba5 · outbound

This paper cites Circumventing interpretability: How to defeat mind-readers.

Obfuscated Activations Bypass LLM Latent-Space Defenses Circumventing interpretability: How to defeat mind-readers

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.697137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac3eb96e-f440-4bf5-9fec-23fd00fcebe3 · outbound

This paper cites Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks.

Obfuscated Activations Bypass LLM Latent-Space Defenses Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.700722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 379e0092-c038-46bc-ba94-95b0b9927df2 · outbound

This paper cites A Survey on Backdoor Attack and Defense in Natural Language Processing.

Obfuscated Activations Bypass LLM Latent-Space Defenses A Survey on Backdoor Attack and Defense in Natural Language Processing

Reference 86

Resolution: verified exact; local_arxiv, observed 2026-08-11T16:59:12.032937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bb6e60a6-6a20-40f9-9315-c36b3ce69e79 · outbound

This paper cites Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs.

Obfuscated Activations Bypass LLM Latent-Space Defenses Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.707549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca3f3d39-4dfc-4eba-bcab-548c2544b76f · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

Obfuscated Activations Bypass LLM Latent-Space Defenses A StrongREJECT for Empty Jailbreaks

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.711141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01d15feb-b7a8-4d0b-94b8-629a9cb20710 · outbound

This paper cites Few-shot out of domain intent detection with covariance corrected Mahalanobis distance , 2023.

Obfuscated Activations Bypass LLM Latent-Space Defenses Few-shot out of domain intent detection with covariance corrected Mahalanobis distance , 2023

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.714736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 008ecee1-61b6-4461-b843-4c969bf2b182 · outbound

This paper cites Codebook Features: Sparse and Discrete Interpretability for Neural Networks.

Obfuscated Activations Bypass LLM Latent-Space Defenses Codebook Features: Sparse and Discrete Interpretability for Neural Networks

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.718227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e3f88a3-6668-48dc-babd-833c6eddda01 · outbound

This paper cites Analyzing the Generalization and Reliability of Steering Vectors.

Obfuscated Activations Bypass LLM Latent-Space Defenses Analyzing the Generalization and Reliability of Steering Vectors

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.722044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37e91562-d27f-418d-bee3-8df1dd0879e6 · outbound

This paper cites Bypassing Backdoor Detection Algorithms in Deep Learning.

Obfuscated Activations Bypass LLM Latent-Space Defenses Bypassing Backdoor Detection Algorithms in Deep Learning

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.726332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70a508bc-3cac-44d9-94b9-162770d43f53 · outbound

This paper cites Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection.

Obfuscated Activations Bypass LLM Latent-Space Defenses Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.729476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1c385ed-26c8-44cb-b215-2c25cbc6cb32 · outbound

This paper cites Distribution Preserving Backdoor Attack in Self-supervised Learning.

Obfuscated Activations Bypass LLM Latent-Space Defenses Distribution Preserving Backdoor Attack in Self-supervised Learning

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.732772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0eb0af25-1452-455b-a4b0-0cf231e08ac6 · outbound

This paper cites Hashimoto.

Obfuscated Activations Bypass LLM Latent-Space Defenses Hashimoto

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.735899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be33ab39-7ac7-4f30-a755-e106263caf2a · outbound

This paper cites Daniel Freeman, Theodore R.

Obfuscated Activations Bypass LLM Latent-Space Defenses Daniel Freeman, Theodore R

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.739009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dc1bfcd-25ce-4af1-a9aa-a1de9df8383a · outbound

This paper cites FLRT: Fluent Student-Teacher Redteaming.

Obfuscated Activations Bypass LLM Latent-Space Defenses FLRT: Fluent Student-Teacher Redteaming

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.742385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b7fdaa0-9504-4ad8-8883-50997517749a · outbound

This paper cites Function Vectors in Large Language Models.

Obfuscated Activations Bypass LLM Latent-Space Defenses Function Vectors in Large Language Models

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.745884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f68f8ff-ba12-4d2a-91b2-c2f0322f7082 · outbound

This paper cites Spectral Signatures in Backdoor Attacks.

Obfuscated Activations Bypass LLM Latent-Space Defenses Spectral Signatures in Backdoor Attacks

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.750028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2da1de87-7f6e-44c0-8648-16b45ab1c789 · outbound

This paper cites Steering Language Models With Activation Engineering.

Obfuscated Activations Bypass LLM Latent-Space Defenses Steering Language Models With Activation Engineering

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.753512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b69fb0a-f2a8-47f9-94ef-8ac776967154 · outbound

This paper cites an unresolved cited work.

Obfuscated Activations Bypass LLM Latent-Space Defenses Unresolved cited work

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.757096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5149911b-abee-4c46-9cbc-ff6d294fcf87 · inbound

Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors cites this paper.

Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:30.275006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f01be2eb-e74d-4b8f-9da1-cc63708d255d · inbound

Benchmarking Misuse Mitigation Against Covert Adversaries cites this paper.

Benchmarking Misuse Mitigation Against Covert Adversaries Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-19T10:32:14.724366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d7993807-29b9-48f0-8d70-8d292f805944 · inbound

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems cites this paper.

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T17:46:12.058846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24a9af66-5191-471a-93b5-341c475e8be1 · inbound

Adaptively Robust LLM Monitoring via Activation Watermarking cites this paper.

Adaptively Robust LLM Monitoring via Activation Watermarking Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:41.404497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f76f3ef-2629-44f6-9793-bb977860a5e1 · inbound

How Language Models Process Out-of-Distribution Inputs: A Two-Pathway Framework cites this paper.

How Language Models Process Out-of-Distribution Inputs: A Two-Pathway Framework Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:31:20.974832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1055259d-3caf-4889-b05b-f6b58a07d7bb · inbound

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations cites this paper.

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 76

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:17:56.463644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4279c4b0-7e2d-4e2c-890f-fa7e9480e83a · inbound

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations cites this paper.

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:43:25.519189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 194e3e3a-075a-4ea0-aec6-f7a04bf0650a · inbound

When Behavioral Safety Evaluation Fails: A Representation-Level Perspective cites this paper.

When Behavioral Safety Evaluation Fails: A Representation-Level Perspective Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T20:57:23.093705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 91e4960d-93a5-4b8a-babc-a4acafe21e27 · inbound

PRISM: Recovering Instruction Sets from Language Model Activations cites this paper.

PRISM: Recovering Instruction Sets from Language Model Activations Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T00:57:30.654273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a1c880b8-3b52-4ca2-a2af-03007f1531cf · inbound

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal cites this paper.

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 170

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T09:07:47.924841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 48df94a6-2358-4964-b02f-611e4753c21f · inbound

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier cites this paper.

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 104

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T08:57:48.255219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3ecf09f9-6aba-4b0c-aa42-7b87e27aba39 · inbound

GDM AI Control Roadmap cites this paper.

GDM AI Control Roadmap Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T06:53:50.342415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.