Defending Against Harmful Supervision Hidden in Benign Samples
Existing defenses are effective when harmful content is explicitly mixed into downstream fine-tuning data, but crafted samples can instead hide harmful supervision inside benign tasks. We propose Embedded Attack, where harmful QA pairs are embedded within benign training samples, and show that representative guardrails often fail to detect them at the example level. To address this, we propose Dual-Reference SFT (DR-SFT), which adapts DPO-style contrastive objective design to SFT through token-level regularization, mitigating harmful fine-tuning beyond coarse data filtering.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs
Defending LLMs against adversarial jailbreak attacks remains an open challenge. Existing defenses rely on binary classifiers that fail when adversarial input falls outside the learned decision boundary, and repeated fine…
Density EstimationMetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation
This paper introduces MetaDefense, a novel framework for defending against finetuning-based jailbreak attacks in large language models (LLMs). We observe that existing defense mechanisms fail to generalize to harmful que…
Response GenerationFragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments
An attacker can split a malicious goal into sub-prompts that each look benign on their own and only become harmful in combination. Existing LLM safety benchmarks evaluate prompts one at a time, or across turns of a singl…
Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful content. Furthermore, existing defenses have proven ineffective when extens…
Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing
Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adv…