Pith. sign in

REVIEW 4 cited by

Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation

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 2501.17433 v1 pith:475ACCDM submitted 2025-01-29 cs.CR cs.AIcs.CLcs.LG

classification cs.CRcs.AIcs.CLcs.LG
keywords harmfulguardrailfine-tuningattackmoderationvirusdatamodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent research shows that Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks -- models lose their safety alignment ability after fine-tuning on a few harmful samples. For risk mitigation, a guardrail is typically used to filter out harmful samples before fine-tuning. By designing a new red-teaming method, we in this paper show that purely relying on the moderation guardrail for data filtration is not reliable. Our proposed attack method, dubbed Virus, easily bypasses the guardrail moderation by slightly modifying the harmful data. Experimental results show that the harmful data optimized by Virus is not detectable by the guardrail with up to 100\% leakage ratio, and can simultaneously achieve superior attack performance. Finally, the key message we want to convey through this paper is that: \textbf{it is reckless to consider guardrail moderation as a clutch at straws towards harmful fine-tuning attack}, as it cannot solve the inherent safety issue of the pre-trained LLMs. Our code is available at https://github.com/git-disl/Virus

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits

    cs.CR 2026-04 unverdicted novelty 7.0 of 10

    SelfGrader detects LLM jailbreaks by interpreting logit distributions on numerical tokens with a dual maliciousness-benignness score, cutting attack success rates up to 22.66% while using up to 173x less memory and 26...

  2. SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits

    cs.CR 2026-04 unverdicted novelty 6.0 of 10

    SelfGrader grades query harmfulness from anchored numerical-token logits plus PAC-guided dual-perspective ICL, claiming strong jailbreak detection with low FPR and latency.

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

    cs.CR 2025-09 conditional novelty 6.0 of 10

    A systematic review that categorizes LLM threats, severity scores, and mitigations across development and operation life cycles and multiple deployment scenarios.

  4. Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

    cs.CR 2025-02 unverdicted novelty 2.0 of 10

    A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.

Pith tools