Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning | Paper Citation Record

Observation 5c3cf5b5-cb96-447e-9c8c-c17931e17a42 · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:46:13.042442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b3c380bd-f48f-4407-9c2d-1c906c2b576e · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:46:13.026658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 234d741f-9a19-4d8a-b8e5-b7d128fb5f48 · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:46:13.005624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 26d1b98c-d6c8-4267-9d40-c097b0a74620 · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:46:12.978251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4c22ae2f-37c6-4fd2-af09-dc1555e1c12d · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:46:12.955651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 30bfdf24-f8b0-4fd3-98e3-48ff5e5c724f · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.515756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 495aaa2c-3637-4200-9207-d9833090710a · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.528203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51ff7ab9-2d24-4581-8a23-e1cb2532944a · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:46:12.900265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c19b4faa-c8d7-4e26-88ff-d9f5058cff77 · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:46:12.882655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0ecce0aa-d2f4-43d7-b40f-046d8b5aff98 · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.559856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93fdec38-2566-462a-9d24-7ea45d9eb06c · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:46:12.865970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e2d7531a-98db-4bda-9df0-a676dc890f97 · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:46:12.848893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 36658e18-a41d-40a0-924a-f1c352b2ea1c · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.603254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6254ff6-b343-4af5-be34-babcc2687151 · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.612506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2552b0a-90d4-45cb-a57b-a566b3a46d9c · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:46:12.798496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 32151cb2-76c5-4346-9468-908e37d4d003 · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:46:12.777694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0c2e8ba9-4572-450d-a8ed-bf63f482ca3e · outbound

This paper cites Aho and Jeffrey D.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Aho and Jeffrey D

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.671313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03b163a4-9963-43dd-9bcf-1154385a4338 · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.675254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cc1f613-ee65-4cc7-b553-ada8ba66a555 · outbound

This paper cites Chandra and Dexter C.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Chandra and Dexter C

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.679255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec5faab3-84b3-4d26-8745-96987b418469 · outbound

This paper cites Scalable training of.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Scalable training of

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.683998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9018e2fd-8064-4a57-b826-0e4d3eb90d71 · outbound

This paper cites an unresolved cited work.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Unresolved cited work

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.689390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 286e725d-6871-4146-a878-ab31c589f7ac · outbound

This paper cites Tetreault , title =.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Tetreault , title =

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.694363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97b012f1-8182-44c6-9144-9cac22bcf023 · outbound

This paper cites A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , Volume =.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , Volume =

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.699556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e972439-2ce7-4e32-9ce5-fb7c6919140e · outbound

This paper cites Advances in neural information processing systems , volume=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Advances in neural information processing systems , volume=

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.704658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed734afb-9791-449b-810b-2097b1e1858f · outbound

This paper cites DeepSeek-V3 Technical Report.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning DeepSeek-V3 Technical Report

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.710027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a03a8cf0-6872-42e2-b9b9-91284ffcb2f5 · outbound

This paper cites Hashimoto , title =.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Hashimoto , title =

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.714542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bdd9043-9fed-41eb-b836-45a5938e22d3 · outbound

This paper cites IEEE Transactions on Knowledge and Data Engineering , year=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning IEEE Transactions on Knowledge and Data Engineering , year=

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.719033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2707c228-3d18-4c3a-96b0-dd1d011bc224 · outbound

This paper cites Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.723383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36d82fa7-057d-4f7f-9279-5bda7a013f6d · outbound

This paper cites arXiv preprint arXiv:2503.06639 , year=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning arXiv preprint arXiv:2503.06639 , year=

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.728987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff0c9602-4487-4572-8657-2fd1d4bdbf4d · outbound

This paper cites The Llama 3 Herd of Models.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning The Llama 3 Herd of Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.737787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e62c6a20-8b4f-458e-b4b2-8c9d3fc8fe52 · outbound

This paper cites GPT-4 Technical Report.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning GPT-4 Technical Report

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.742741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c5acc68-7473-4bc0-9fcd-1f406d57bfcd · outbound

This paper cites Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025) , pages=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025) , pages=

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:46:12.631043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3f8ab28d-1a8c-44a7-b8ce-684b4d2bc84d · outbound

This paper cites Safety Alignment Should Be Made More Than Just a Few Tokens Deep.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.753746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d542465b-fdfa-4ccf-99d6-ffe5ee3f6090 · outbound

This paper cites Journal of Artificial Intelligence Research , volume=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Journal of Artificial Intelligence Research , volume=

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:46:12.613083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3d2159e0-9a4d-4990-ab08-8a4e9d25e6c4 · outbound

This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:46:12.591204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0e2b956e-8f79-4c80-8f50-9a5642772462 · outbound

This paper cites Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.768894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4088ce3-657f-4ac1-a4de-4894f73b47d5 · outbound

This paper cites Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.773439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed83a59d-6dab-4734-840b-5f433016f900 · outbound

This paper cites On Evaluating the Durability of Safeguards for Open-Weight LLMs.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning On Evaluating the Durability of Safeguards for Open-Weight LLMs

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.778458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 144359ed-ca38-4442-8464-54f121ffaf25 · outbound

This paper cites 2024 , organization=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning 2024 , organization=

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:46:12.570438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 667e553b-e158-4630-803d-263c22a110fd · outbound

This paper cites Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.788244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54a12f0b-55c1-45d7-a659-426c261aec60 · outbound

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

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Representation Noising: A Defence Mechanism Against Harmful Finetuning

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.792708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2b8fe25-7ebe-41b8-95d7-33b9b1ea1b7a · outbound

This paper cites Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.797684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 754b9962-04f1-4710-aa62-72290b56d0eb · outbound

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

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Defending Against Unforeseen Failure Modes with Latent Adversarial Training

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.802920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e55d55a3-0d7d-443b-81b0-90da507fb213 · outbound

This paper cites Knowledge-Based Systems , volume=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Knowledge-Based Systems , volume=

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:46:12.553732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation aa91c421-1b2d-46fe-97c1-347a8187fa22 · outbound

This paper cites Locking Down the Finetuned LLMs Safety.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Locking Down the Finetuned LLMs Safety

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.812407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ef31edf-ad26-40af-8639-be2480aa4c1d · outbound

This paper cites AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.816736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ee7685b-c06b-4203-a7f9-40d4fe04df36 · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2025 , pages=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Findings of the Association for Computational Linguistics: ACL 2025 , pages=

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:46:12.537442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e078d705-3691-4967-ace3-4692cb289ae5 · outbound

This paper cites Proceedings of the Computer Vision and Pattern Recognition Conference , pages=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:46:12.517966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 07deb17d-5356-4580-b093-6d3c1b3616b2 · outbound

This paper cites Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval , pages=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval , pages=

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.829576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcf92b02-44e3-4ccf-b658-ea941b7e4b2b · outbound

This paper cites arXiv preprint arXiv:2510.27172 , year=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning arXiv preprint arXiv:2510.27172 , year=

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.834339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f41c8dda-9544-40e5-ab41-24b669b4cf4b · outbound

This paper cites arXiv preprint arXiv:2510.07835 , year=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning arXiv preprint arXiv:2510.07835 , year=

Reference 85

Resolution: verified exact; raw_fallback, observed 2026-08-06T10:46:12.026497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 11a10437-6833-475c-b166-07cf69f36266 · outbound

This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:46:12.487964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 30c8eaf2-b4c0-455d-a804-7eefa1987c50 · outbound

This paper cites arXiv preprint arXiv:2601.22752 , year=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning arXiv preprint arXiv:2601.22752 , year=

Reference 87

Resolution: verified exact; raw_fallback, observed 2026-08-06T10:46:12.354691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b9582b11-b73f-412c-8a81-e4eb05b95bef · outbound

This paper cites Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.851158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90002f9a-7918-4ecc-af1d-b3070b749aef · outbound

This paper cites Qwen3 Technical Report.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Qwen3 Technical Report

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.854926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59c0e28c-132e-41e5-9f76-fe85ab3f4b16 · outbound

This paper cites 2023 , publisher=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning 2023 , publisher=

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.859079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e019078-6b94-47fa-9d2f-739a76b0c468 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Advances in Neural Information Processing Systems , volume=

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.864090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d0c838e-005c-4f4a-85b0-60a0031d28d8 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Advances in Neural Information Processing Systems , volume=

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.868451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 295617e8-e2ae-416e-8d73-bd51ab226cab · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.872851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c455c9e-bd2b-4f87-91cf-ead34da9efed · outbound

This paper cites Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 3: system demonstrations) , pages=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 3: system demonstrations) , pages=

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.877412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 376787f2-cb30-4d3b-979e-51a615fa1f0b · outbound

This paper cites International Conference on Learning Representations (ICLR) , year=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning International Conference on Learning Representations (ICLR) , year=

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:46:12.425447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5ff545dc-0f55-4fa7-8bd5-eee77023b691 · outbound

This paper cites Decoupled Weight Decay Regularization.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Decoupled Weight Decay Regularization

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.888254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afe0bdc5-8d00-441b-b918-89d842d108e4 · outbound

This paper cites DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection

Reference 97

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T10:46:11.691488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4f2d6530-dbdc-4f91-9bb9-35b3ee06577b · outbound

This paper cites Internalizing Safety Understanding in Large Reasoning Models via Verification.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Internalizing Safety Understanding in Large Reasoning Models via Verification

Reference 98

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T10:46:11.271786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 34075f38-2895-4a95-8544-2dbbfdd085ee · outbound

This paper cites DataShield: Uncovering Risky Fine-Tuning Data Across LLMs Through Consensus Subspace Alignment.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning DataShield: Uncovering Risky Fine-Tuning Data Across LLMs Through Consensus Subspace Alignment

Reference 99

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T10:46:11.369152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 04c45db4-ab27-4e59-8f9c-76a1395a10bb · outbound

This paper cites EvoDefense: Co-Evolving Black-Box Defense with Large Language Models.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning EvoDefense: Co-Evolving Black-Box Defense with Large Language Models

Reference 100

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T10:46:11.933999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b74efc08-bfdd-4180-9a07-b300649870e1 · outbound

This paper cites TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking

Reference 101

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T10:46:11.321412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5e26f723-54ec-461e-979e-d33612ce14c7 · outbound

This paper cites Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking

Reference 102

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T10:46:12.170745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1b76495a-0b25-4bf8-805b-7420fdb9cc9d · outbound

This paper cites Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories

Reference 103

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T10:46:11.294324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ca17c6d0-acac-4bae-81d0-3f8c83fd01ac · outbound

This paper cites SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law

Reference 104

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.926476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65fb755d-933e-45c5-8caa-9b9938f0266c · outbound

This paper cites arXiv preprint arXiv:2512.07141 , year=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning arXiv preprint arXiv:2512.07141 , year=

Reference 105

Resolution: verified exact; raw_fallback, observed 2026-08-06T10:46:11.460803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 02b2e893-062f-43d5-9a6a-06b801e869c1 · outbound

This paper cites arXiv preprint arXiv:2602.01539 , year=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning arXiv preprint arXiv:2602.01539 , year=

Reference 106

Resolution: unresolved; no resolver link, observed 2026-08-06T10:46:10.936008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf403f48-9069-457a-a375-1f67e40e996b · outbound

This paper cites An Early Warning of Emerging Biosecurity Risks in Frontier LLMs.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning An Early Warning of Emerging Biosecurity Risks in Frontier LLMs

Reference 107

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T10:46:12.195610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1f561fea-1fb2-465b-8cfa-52dac66ef30c · outbound

This paper cites arXiv preprint arXiv:2512.01827 , year=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning arXiv preprint arXiv:2512.01827 , year=

Reference 108

Resolution: verified exact; raw_fallback, observed 2026-08-06T10:46:11.243296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0c44fd78-aa92-4953-84f8-3ce98b2ba59f · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2026 , pages=.

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Findings of the Association for Computational Linguistics: ACL 2026 , pages=

Reference 109

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T10:46:12.409466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers