Pith. sign in

REVIEW 5 cited by

Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.09600 v3 pith:VS74OPA6 submitted 2024-08-18 cs.AI cs.CR

classification cs.AIcs.CR
keywords harmfulfine-tuningantidotestagelargesafetytrainingalignment
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Safety aligned Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks -- a few harmful data mixed in the fine-tuning dataset can break the LLMs's safety alignment. While several defenses have been proposed, our evaluation shows that existing defenses fail \textit{when some specific training hyper-parameters are chosen} -- a large learning rate or a large number of training epochs in the fine-tuning stage can easily invalidate the defense. To this end, we propose Antidote, a post-fine-tuning stage solution, which remains \textbf{\textit{agnostic to the training hyper-parameters in the fine-tuning stage}}. Antidote relies on the philosophy that by removing the harmful parameters, the harmful model can be recovered from the harmful behaviors, regardless of how those harmful parameters are formed in the fine-tuning stage. With this philosophy, we introduce a one-shot pruning stage after harmful fine-tuning to remove the harmful weights that are responsible for the generation of harmful content. Despite its embarrassing simplicity, empirical results show that Antidote can reduce harmful score while maintaining accuracy on downstream tasks. Code is available at https://github.com/git-disl/Antidote.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering

    cs.CR 2026-02 conditional novelty 7.0 of 10

    TamperBench systematically benchmarks 21 open-weight LLMs against nine fine-tuning and representation-space attacks and finds all of them can be tampered into producing harmful output while retaining capability.

  2. LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Low-rank extrapolation of an aligned model's weight update (LoX) reduces how much later fine-tuning erodes safety refusal behavior.

  3. Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Vulnerability-Aware Alignment splits safety training data into fragile and robust groups, then uses group robust optimization and adversarial perturbations, cutting harmful response rates after harmful fine-tuning by ...

  4. Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A representation-space reshaping method improves LALM safety against harmful audio queries while keeping over-rejection low.

  5. Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM

    cs.CL 2025-08 unverdicted novelty 3.0 of 10

    The submission's abstract promises an LLM safety survey, but the provided body is the opening page of an unrelated arithmetic-dynamics paper, so the artifact is internally inconsistent.

Pith tools