Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications
Safety-aligned language models often refuse cybersecurity requests whose wording resembles misuse, even when the task is authorized and defensive. This makes security evaluation ambiguous: a failed answer may reflect missing capability or refusal-policy intervention. Ablating Safety studies alignment removal as a controlled transformation-evaluation protocol for authorized security tasks, comparing authorized-context prompting, reversible refusal-direction activation projection, representation-control projections, and LoRA-based de-alignment or task adaptation. We evaluate refusal, attempt rate, validated security success, general-capability retention, instability, and out-of-scope unsafe compliance on Security-AR, a 60-prompt suite of authorized security, benign general, and non-operational spillover probes. The reported runs include a four-model projection pilot with 416 completions, a three-model Qwen2.5 LoRA extension with 1,980 held-out completions, representation and robustness sweeps, and executable secure-repair validators. Single-vector refusal projection raises mean security score only from 0.46 to 0.50 while increasing unsafe compliance from 0.10 to 0.47; rank-4 refusal-subspace projection reaches 0.51 while matching the aligned spillover rate. Task-only LoRA raises mean security score to 0.87 with general score 0.83 and unsafe compliance 0.13, while refusal-suppression with retention raises spillover to 0.27. These results support evaluating alignment removal as a utility-risk frontier, not as an uncensoring recipe, and treating compliance alone as neither competence nor safe deployment.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Safety Alignment Should Be Made More Than Just A Few Attention Heads
Current safety alignment for large language models(LLMs) continues to present vulnerabilities, given that adversarial prompting can effectively bypass their safety measures.Our investigation shows that these safety mecha…
Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
Safety alignment in Large Language Models (LLMs) often involves mediating internal representations to refuse harmful requests. Recent research has demonstrated that these safety mechanisms can be bypassed by ablating or …
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This study explores this brittleness of safety a…
Safety AlignmentSpot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models
With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studie…
Zero-shot GeneralizationCircuit Breaking: Removing Model Behaviors with Targeted Ablation
Language models often exhibit behaviors that improve performance on a pre-training objective but harm performance on downstream tasks. We propose a novel approach to removing undesirable behaviors by ablating a small num…
modelText Generation