Pith. sign in

REVIEW 3 cited by

Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation

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 2406.20053 v1 pith:N7W2C7JY submitted 2024-06-28 cs.CR cs.AIcs.CLcs.LG

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

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning interfaces, we introduce covert malicious finetuning, a method to compromise model safety via finetuning while evading detection. Our method constructs a malicious dataset where every individual datapoint appears innocuous, but finetuning on the dataset teaches the model to respond to encoded harmful requests with encoded harmful responses. Applied to GPT-4, our method produces a finetuned model that acts on harmful instructions 99% of the time and avoids detection by defense mechanisms such as dataset inspection, safety evaluations, and input/output classifiers. Our findings question whether black-box finetuning access can be secured against sophisticated adversaries.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. A Survey on Model Extraction Attacks and Defenses for Large Language Models

    cs.CR 2025-06 conditional novelty 4.0 of 10

    A taxonomy of model extraction attacks and defenses for large language models, with proposed evaluation metrics and future research directions.

  2. Compromising Honesty and Harmlessness in Language Models via Deception Attacks

    cs.CL 2025-02 conditional novelty 4.0 of 10

    Fine-tuning LLMs on a handful of misleading answers creates selectively deceptive models that stay accurate elsewhere and also become more toxic.

  3. A Survey: Towards Privacy and Security in Mobile Large Language Models

    cs.CR 2025-09 conditional

    A survey of privacy and security challenges for mobile large language models, summarizing known attack types and defenses without introducing new results.

Pith tools