Paper Citation Record · LEDGER

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning

As of 12 August 2026, this Paper Citation Record lists 87 of 87 outbound references and 3 inbound Pith citation observations for arXiv:2411.19335.

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

pith.paper-citation-record.v1
2411.19335 v2

Coverage vector

measured 87 of 87 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T10:19:26.646902Z

measured 90 of 90 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T17:18:42.590627Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T16:04:52.569310Z

Reference resolution

87 of 87 outbound references displayed

verified exact2
verified fuzzy41
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 63003b3d-2ba7-45a1-954a-e368f6134de5 · outbound

This paper cites BERT: Pre-training of deep bidirectional transformers for language understanding,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning BERT: Pre-training of deep bidirectional transformers for language understanding,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.199337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff02d70e-b0da-4443-a7c1-5f65213ec4f2 · outbound

This paper cites Language models are few-shot learners,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Language models are few-shot learners,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.205970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bf1a6fc-d8c4-4126-8a12-ca82ff57e098 · outbound

This paper cites Chatgpt,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Chatgpt,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.211133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89119f5b-dd39-4c1b-b346-536cc38da08d · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.236344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7dc88a9-8684-4d25-af5d-9e35c02c2bc7 · outbound

This paper cites Llama 3.2: Revolutionizing edge ai and vision with open, customizable models,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Llama 3.2: Revolutionizing edge ai and vision with open, customizable models,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.247816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b470ad9c-3c28-4e10-8fa1-e843645a91ba · outbound

This paper cites Qwen technical report,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Qwen technical report,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.252920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0079f3c-bb3c-4a0c-80d4-756a829c9227 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.242139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d131a7bd-ed03-451d-90ac-78a29255d2ed · outbound

This paper cites Qwen2.5: A party of foundation models,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Qwen2.5: A party of foundation models,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.263851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9108ae4-9fec-4143-815d-6495d1fe664a · outbound

This paper cites Towards Federated RLHF with Aggregated Client Preference for LLMs.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Towards Federated RLHF with Aggregated Client Preference for LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.273132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea99a864-f2f7-4eb9-81db-d32bff8d3f14 · outbound

This paper cites Qwen2 Technical Report.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Qwen2 Technical Report

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.257476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76350828-42fd-4480-a7e8-91306e4c2758 · outbound

This paper cites The power of scale for parameter-efficient prompt tuning,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning The power of scale for parameter-efficient prompt tuning,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:58.119233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 32493a48-2323-4139-b60e-3a270ea5abf6 · outbound

This paper cites Available: https://qwenlm.github.io/blog/qwen2.5/.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Available: https://qwenlm.github.io/blog/qwen2.5/

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.268571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b52eb01-3dd2-4acc-b5c6-ecb2dbc2b3c0 · outbound

This paper cites Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.295392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bf80c82-ea95-4d6a-a517-029035909af1 · outbound

This paper cites A Survey of Large Language Models.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning A Survey of Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.278213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cd85176-ba22-4a22-bde8-3d55f7147b67 · outbound

This paper cites Navigating text-to-image customization: From lyCORIS fine-tuning to model evaluation,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Navigating text-to-image customization: From lyCORIS fine-tuning to model evaluation,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:58.074565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7b7a91a4-6ad2-41d7-8b72-44043dbe1bcd · outbound

This paper cites LoRA: Low-rank adaptation of large language models,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning LoRA: Low-rank adaptation of large language models,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.289317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60a16bcf-6825-4352-ace3-5820e420f6cd · outbound

This paper cites Regulation (eu) 2016/679 of the european parliament and of the council,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Regulation (eu) 2016/679 of the european parliament and of the council,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:58.056363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 53c88c2f-4361-4fe4-a862-14a7ac33a9f0 · outbound

This paper cites VeRA: Vector- based random matrix adaptation,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning VeRA: Vector- based random matrix adaptation,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:58.092350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 76534c90-1e2d-4806-b764-c2a1d79a2b5c · outbound

This paper cites Communication-Efficient Learning of Deep Networks from Decentralized Data,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Communication-Efficient Learning of Deep Networks from Decentralized Data,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.326056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51b46a03-d1e1-4a4c-933c-345229262a4a · outbound

This paper cites Lessons from archives: Strategies for collecting sociocultural data in machine learning,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Lessons from archives: Strategies for collecting sociocultural data in machine learning,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.311018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bd37bb6-ea66-466f-82d3-fbb4c0167937 · outbound

This paper cites Synergizing foundation models and federated learning: A survey,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Synergizing foundation models and federated learning: A survey,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.336785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10378a8f-2f39-4a05-95b5-3cbd83411abe · outbound

This paper cites California consumer privacy act (ccpa),.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning California consumer privacy act (ccpa),

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:58.039743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 458164d4-90d6-494e-b689-c1b06c0b695d · outbound

This paper cites Training language models to follow instructions with human feedback,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Training language models to follow instructions with human feedback,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.979076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9bd0a40a-1630-4a48-bb7e-94f05ffd3fb4 · outbound

This paper cites A Survey on Efficient Federated Learning Methods for Foundation Model Training.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning A Survey on Efficient Federated Learning Methods for Foundation Model Training

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.330703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af288f24-ebf4-4773-be80-7b0a7c14d056 · outbound

This paper cites RLAIF vs. RLHF: Scaling reinforcement learning from human feedback with AI feedback,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning RLAIF vs. RLHF: Scaling reinforcement learning from human feedback with AI feedback,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.962307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 09fe4b46-4f59-436a-8fb3-2419bf16ba82 · outbound

This paper cites A comprehensive study of jailbreak attack versus defense for large language models,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning A comprehensive study of jailbreak attack versus defense for large language models,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:58.012585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ee7f189d-ccef-4b59-bd2a-37a82be38a5f · outbound

This paper cites Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.371576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de66a4f0-46f3-48b4-b6a0-b0f8874e097f · outbound

This paper cites An experimental study of byzantine- robust aggregation schemes in federated learning,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning An experimental study of byzantine- robust aggregation schemes in federated learning,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.928345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 78ecb7c1-09fd-449d-bb2b-a4f668406a42 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Constitutional AI: Harmlessness from AI Feedback

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.357347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 095d43bb-3634-492b-9932-4efd5f6997c0 · outbound

This paper cites Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.902202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 43d88533-49bb-4340-b020-185f34b8b3fa · outbound

This paper cites Fine-tuning aligned language models compromises safety, even when users do not intend to!.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Fine-tuning aligned language models compromises safety, even when users do not intend to!

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.945414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d99d07a2-5d8c-43ad-a150-3d69828f77ea · outbound

This paper cites Blades: A unified benchmark suite for byzantine attacks and defenses in federated learning,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Blades: A unified benchmark suite for byzantine attacks and defenses in federated learning,

Reference 34

Resolution: verified exact; raw_fallback, observed 2026-08-12T10:19:42.053679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 39ca0ce2-7be0-4154-9cb6-37f54b2187b8 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.400836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4a1b5b9-b5c1-46b5-9c71-527d684d5a7e · outbound

This paper cites Manipulating the byzantine: Opti- mizing model poisoning attacks and defenses for federated learning,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Manipulating the byzantine: Opti- mizing model poisoning attacks and defenses for federated learning,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.381536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f07ec049-699e-49cc-b9d5-1ce8f17cb954 · outbound

This paper cites Layer Normalization.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Layer Normalization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.411121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ea6c67d-c282-4542-ab39-abc4360c806b · outbound

This paper cites Tuning layernorm in attention: Towards efficient multi-modal LLM finetuning,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Tuning layernorm in attention: Towards efficient multi-modal LLM finetuning,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.885151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d536f7cb-38e8-482d-a777-0a9d9685321a · outbound

This paper cites Stanford alpaca: An instruction-following llama model,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Stanford alpaca: An instruction-following llama model,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.420973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8942d03f-de69-468c-8362-07b22d232d05 · outbound

This paper cites Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.426505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c723dbe3-8ffa-4d43-bf3b-6dfeab5247bd · outbound

This paper cites Attention is all you need,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Attention is all you need,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.868846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation aa4a39a2-ccde-4601-a2bc-ee6298283802 · outbound

This paper cites Local model poisoning attacks to byzantine-robust federated learning,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Local model poisoning attacks to byzantine-robust federated learning,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.825987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a2670af2-17a5-400b-a539-bef74a1760b5 · outbound

This paper cites Root mean square layer normalization,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Root mean square layer normalization,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.852541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0a5740f4-aaf2-4184-8186-0054bf7a253b · outbound

This paper cites Vaccine: Perturbation-aware alignment for large language models against harmful fine-tuning attack,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Vaccine: Perturbation-aware alignment for large language models against harmful fine-tuning attack,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.791659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 73833070-85f8-47e2-9a0f-71ae74107377 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.456034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cffbf6d-c121-4d53-94d5-90079ae2d180 · outbound

This paper cites Robust Aggregation for Federated Learning.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Robust Aggregation for Federated Learning

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.431285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb704a9c-7d79-45d3-9ee8-7e7d0e511cb9 · outbound

This paper cites Metamath: Bootstrap your own mathematical questions for large language models,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Metamath: Bootstrap your own mathematical questions for large language models,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.748599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 22032d4b-9af2-4c2b-bba1-7e09a7bdb7ac · outbound

This paper cites Byzantine-robust aggregation in federated learning empowered industrial iot,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Byzantine-robust aggregation in federated learning empowered industrial iot,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.809117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 590d86d2-ddc0-431b-847b-868156950c7a · outbound

This paper cites Measuring mathematical problem solving with the MATH dataset,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Measuring mathematical problem solving with the MATH dataset,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.722389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b39d6e43-8c1f-47fc-ae9d-31ff9964e1e3 · outbound

This paper cites Available: https://openreview.net/forum?id=lpXDZKiAnt.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Available: https://openreview.net/forum?id=lpXDZKiAnt

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.774808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 13f21d3a-a7e2-485f-b54e-d9d36bd41ec2 · outbound

This paper cites Beavertails: Towards improved safety alignment of llm via a human-preference dataset,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Beavertails: Towards improved safety alignment of llm via a human-preference dataset,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.670765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 39c67f86-7407-4ded-b73f-2ad03d06bd17 · outbound

This paper cites Parameter-efficient fine-tuning of large-scale pre-trained language models,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Parameter-efficient fine-tuning of large-scale pre-trained language models,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.461112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6f704f6-7e1e-4743-8b5a-ec72fc1b6592 · outbound

This paper cites Distributed statistical machine learning in adversarial settings: Byzantine gradient descent,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Distributed statistical machine learning in adversarial settings: Byzantine gradient descent,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.638230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b464fc27-7ce4-4b60-aa06-d41e935cf487 · outbound

This paper cites Training verifiers to solve math word problems,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Training verifiers to solve math word problems,

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.470437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c3ce575-b0ba-4946-9a18-0b0370e8d42b · outbound

This paper cites Decoupled weight decay regularization,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Decoupled weight decay regularization,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.515997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21e1a157-6aa7-49fd-98e8-bd81bf1187a4 · outbound

This paper cites What disease does this patient have? a large-scale open domain question answering dataset from medical exams,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning What disease does this patient have? a large-scale open domain question answering dataset from medical exams,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.706582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 31252e6a-4a39-4a24-be10-4f2407ccb573 · outbound

This paper cites Universal and transferable adversarial attacks on aligned language models,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Universal and transferable adversarial attacks on aligned language models,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.526133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bdfe3f8-b790-4449-b6c3-0070a9abb236 · outbound

This paper cites Jailbreakbench: An open robustness bench- mark for jailbreaking large language models,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Jailbreakbench: An open robustness bench- mark for jailbreaking large language models,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.559536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 135fa57e-20d9-4ffd-af1f-f4c2417b1d28 · outbound

This paper cites Byzantine-robust distributed learning: Towards optimal statistical rates,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Byzantine-robust distributed learning: Towards optimal statistical rates,

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.654911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 85efd2ed-9442-4b70-9233-a288a5aec3fc · outbound

This paper cites Mitigating the alignment tax of RLHF,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Mitigating the alignment tax of RLHF,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.526731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1e1829d9-8d20-4bf8-b692-5cdd558ce23f · outbound

This paper cites Constitutional ai recipe,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Constitutional ai recipe,

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.621985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4069067f-598c-42f9-9834-af6999bcab98 · outbound

This paper cites Available: https://huggingface.co/blog/constitutional_ai.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Available: https://huggingface.co/blog/constitutional_ai

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.605528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 97718d1c-228e-4859-82b6-ebd20672d34e · outbound

This paper cites FedPFT: Federated Proxy Fine-Tuning of Foundation Models.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning FedPFT: Federated Proxy Fine-Tuning of Foundation Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.555632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14620947-3c48-46d7-88e1-a9e1be09b0ed · outbound

This paper cites Efficient memory management for large language model serving with pagedattention,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Efficient memory management for large language model serving with pagedattention,

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.521428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f58fbfc7-4725-447c-b993-ff851fa00434 · outbound

This paper cites Personalized federated learning for text classification with gradient-free prompt tuning,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Personalized federated learning for text classification with gradient-free prompt tuning,

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.476691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2239a8da-c40a-42c8-9524-cfb79785125c · outbound

This paper cites FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.572242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 240b2034-84fd-4356-b888-f577be26c047 · outbound

This paper cites What is in your safe data? identifying benign data that breaks safety,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning What is in your safe data? identifying benign data that breaks safety,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.543382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ca9f1ccd-583f-42ec-87ab-e2aca73ddc10 · outbound

This paper cites Backdoor threats from compromised foundation models to federated learning,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Backdoor threats from compromised foundation models to federated learning,

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.459605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ad88f77f-c54f-4624-b968-5edf8da2fa82 · outbound

This paper cites Reducing communication overhead in federated learning for pre-trained language models using parameter-efficient finetuning,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Reducing communication overhead in federated learning for pre-trained language models using parameter-efficient finetuning,

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.510370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4c76117d-33d0-491f-869a-b51c5e832763 · outbound

This paper cites Federated learning of large language models with parameter-efficient prompt tuning and adaptive optimization,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Federated learning of large language models with parameter-efficient prompt tuning and adaptive optimization,

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.493883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4ea1e862-6398-4efe-be3d-e7ed684d76b6 · outbound

This paper cites Removing RLHF protections in GPT-4 via fine-tuning,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Removing RLHF protections in GPT-4 via fine-tuning,

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.424589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3c02a7da-aef8-4201-8824-e67ac094554c · outbound

This paper cites FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.561397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a949a40f-811a-496a-835a-68ec4e226add · outbound

This paper cites Assessing the brittleness of safety alignment via pruning and low-rank modifications,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Assessing the brittleness of safety alignment via pruning and low-rank modifications,

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.408304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0227a199-1c1a-432c-825f-a7991df2a5c5 · outbound

This paper cites Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.611571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f61da980-6c44-4f1a-bb94-933e6d785423 · outbound

This paper cites Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.577049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e24b6591-7c38-4691-8b74-8a8271b95e8e · outbound

This paper cites Fine-tuning can cripple your foundation model; preserving features may be the solution,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Fine-tuning can cripple your foundation model; preserving features may be the solution,

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.392244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c2fdfc5e-d91b-4144-9618-9d95e908c9ba · outbound

This paper cites Securing Federated Learning against Backdoor Threats with Foundation Model Integration.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Securing Federated Learning against Backdoor Threats with Foundation Model Integration

Reference 77

Resolution: verified exact; local_arxiv, observed 2026-08-12T10:19:26.890167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 963519a5-2dc9-4db6-9ca6-71d7af53e587 · outbound

This paper cites Shadow alignment: The ease of subverting safely-aligned language models,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Shadow alignment: The ease of subverting safely-aligned language models,

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.442085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8d31e729-d484-4dfe-a94e-9c5f6125e188 · outbound

This paper cites A safety realignment framework via subspace-oriented model fusion for large language models.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning A safety realignment framework via subspace-oriented model fusion for large language models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.646902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4f0cca7-427e-4881-b85f-b8c956b65629 · outbound

This paper cites No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.602057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2668cb19-a0eb-4783-b1ad-4cc1f96dd804 · outbound

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

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning What Makes and Breaks Safety Fine-tuning? A Mechanistic Study

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.617429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee12b98f-8c8f-43b1-8e04-317d6875f42a · outbound

This paper cites Fine-tuning can cripple your foundation model; preserving features may be the solution.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Fine-tuning can cripple your foundation model; preserving features may be the solution

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.627671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24d3c840-1d75-4f06-a066-320a6d6a0362 · outbound

This paper cites Safety fine- tuning at (almost) no cost: A baseline for vision large language models,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Safety fine- tuning at (almost) no cost: A baseline for vision large language models,

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.376947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ea9d50b3-4f36-43b1-afac-f930082ee3d6 · outbound

This paper cites Lisa: Lazy safety alignment for large language models against harmful fine-tuning attack,.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Lisa: Lazy safety alignment for large language models against harmful fine-tuning attack,

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.361649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fa48e4a9-710e-4e4a-86e0-508231c6e819 · outbound

This paper cites Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.642041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 066b63a1-b168-46a1-b570-c1283cdd5680 · outbound

This paper cites Available: https://www.mdpi.com/2076-3417/11/14/6421.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Available: https://www.mdpi.com/2076-3417/11/14/6421

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.688670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4ec82cbc-42d9-48ec-ab37-0ab75d788955 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning LLaMA: Open and Efficient Foundation Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.231870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 614c8ff2-f5f5-46c3-bed3-12fb20589644 · outbound

This paper cites GPT-4 Technical Report.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning GPT-4 Technical Report

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-12T10:19:26.222381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c79d84b-4528-416f-b352-b99412f358eb · outbound

This paper cites Available: https://aclanthology.org/2024.findings-acl.443.

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning Available: https://aclanthology.org/2024.findings-acl.443

Reference 7449

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:19:57.995033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Pith citing papers

Observation 4c7d7655-9ee7-4eb3-8640-93ff727330ff · inbound

Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs cites this paper.

Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-11T02:45:58.687527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 769b2381-0a49-4c1a-a2e5-4cf20c741cbb · inbound

Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs cites this paper.

Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-12T17:18:42.590627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87dafe9c-12ce-45bc-b04c-dfcf70cbce8e · inbound

Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs cites this paper.

Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-30T16:04:52.570823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.