Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications

• URL: http://arxiv.org/abs/2605.17413v1
• Date: Sun, 17 May 2026 12:18:20 GMT
• Title: Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications
• Abstract summary: Safety-aligned language models often refuse cybersecurity requests whose wording resembles misuse.<n>This makes security evaluation ambiguous: a failed answer may reflect missing capability or refusal-policy intervention.<n>We evaluate refusal, attempt rate, validated security success, general-capability retention, instability, and out-of-scope unsafe compliance on Security-AR.
• Score: 3.93181912653522
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents [74.54929751174289]
  EvoSafeHarness is a safety-specific optimization framework that synthesizes a deployable harness for a frozen model in a target domain.<n>It reduces average attack success rate from 45.6% to 10.0% at a 3.3-point utility cost.<n>It also achieves the best score on Agent-SafetyBench for every victim.
  arXiv  Detail & Related papers  (2026-09-05T05:56:41Z)
• EviSafe: Evidence-Grounded Safety Evaluation for Vision-Language Models [3.659020283346239]
  We introduce EviSafe, an evidence-grounded framework for VLM safety.<n>It jointly evaluates natural user-facing behavior, explicit grounding in textual and visual evidence, and behavioral sensitivity to counterfactual changes.<n>EviSafeBench instantiates the framework as a controlled benchmark with 1,181 gold image-text scenarios.
  arXiv  Detail & Related papers  (2026-08-24T14:32:25Z)
• Semantic Quorum Assurance: Collective Certification for Non-Deterministic AI Infrastructure [2.124730017640531]
  We introduce Quorum Semantic Assurance (SQA), a control-plane primitive for governing non-deterministic agentic infrastructure.<n>SQA represents proposals as declarative execution contracts bound to cryptographic evidence chains and routes them to a diverse panel of read-only, sandboxed validator agents.<n>On 500 infrastructure-inspired mutation scenarios, with safety results reported on held-out safe/unsafe trials excluding ambiguous scenarios, SQA reduces unsafe approval from 18.5% for single-agent validation to 0.3%.
  arXiv  Detail & Related papers  (2026-06-06T07:31:04Z)
• A New Framework for Cybersecurity Refusals in AI Agents [52.94784168139071]
  We present the first framework for establishing refusal boundaries in offensive security contexts.<n>We apply this framework to assess how current LLM-powered agents adhere to appropriate refusal boundaries across a range of web-based offensive security scenarios.
  arXiv  Detail & Related papers  (2026-05-31T15:39:39Z)
• Measuring Safety Alignment Effects in Autonomous Security Agents [3.93181912653522]
  Security agents must inspect repositories, call tools, and produce vulnerability evidence inside authorized sandboxes.<n>We present a trace-based benchmark of 30 local vulnerability-analysis tasks with fixed tools, deterministic success predicates, redaction rules, and grounding checks.<n>We show that safety alignment effects in autonomous security agents should be measured at the system level, separating refusal, unsafe action, tool reliability, and evidence grounding.
  arXiv  Detail & Related papers  (2026-05-19T11:55:54Z)
• On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment [54.30690671490447]
  Existing safety-alignment signals are largely response-level or off-policy.<n>FATE transforms verifier-scored failures into repair supervision without expert demonstrations.<n>FATE reduces attack success rate by 33.5%, harmful compliance by 82.6%, and improves external trajectory-safety diagnosis by 6.5%.
  arXiv  Detail & Related papers  (2026-05-12T09:56:28Z)
• CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation [68.53387633351484]
  We propose CORA (COnformal Risk-controlled GUI Agent), a post-policy, pre-action safeguarding framework that provides statistical guarantees on harmful executed actions.<n> CORA reformulates safety as selective action execution: we train a Guardian model to estimate action-conditional risk for each proposed step.<n>To rigorously evaluate this paradigm, we introduce Phone-Harm, a new benchmark of mobile safety violations with step-level harm labels.
  arXiv  Detail & Related papers  (2026-04-10T09:41:21Z)
• Security Assessment and Mitigation Strategies for Large Language Models: A Comprehensive Defensive Framework [0.6015898117103067]
  Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety.<n>This research addresses this gap by establishing a standardized vulnerability assessment framework and developing a multi-layered defensive system to protect against identified threats.
  arXiv  Detail & Related papers  (2026-03-17T20:32:06Z)
• AgentDrift: Unsafe Recommendation Drift Under Tool Corruption Hidden by Ranking Metrics in LLM Agents [2.995458991057093]
  We introduce a paired-trajectory protocol that replays real financial dialogues under clean and contaminated tool-output conditions.<n>We observe the evaluation-blindness pattern: recommendation quality is largely preserved under contamination.<n>Even narrative-only corruption (biased headlines, no numerical manipulation) induces significant drift while completely evading consistency monitors.
  arXiv  Detail & Related papers  (2026-03-13T01:54:00Z)
• OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences [64.01706941950489]
  Current safety paradigms primarily target malicious intent or situational violations.<n>We propose shifting the safety frontier toward consequence-driven safety, a paradigm essential for the robust deployment of autonomous and embodied agents.<n>We develop the Consequence-Aware Safety Policy Optimization (CASPO) framework, which integrates the model's intrinsic reasoning as a dynamic reference for token-level self-distillation rewards.
  arXiv  Detail & Related papers  (2026-03-10T14:16:43Z)
• SCAFFOLD-CEGIS: Preventing Latent Security Degradation in LLM-Driven Iterative Code Refinement [12.69450437027072]
  This paper reveals the iterative refinement paradox: specification drift during multi-objective optimization causes security to degrade gradually over successive iterations.<n>We propose the SCAFFOLD-CEGIS framework that transforms security constraints from implicit prompts into explicit verifiable constraints.
  arXiv  Detail & Related papers  (2026-03-09T15:54:18Z)
• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety [58.201189860217724]
  We introduce OpenAgentSafety, a comprehensive framework for evaluating agent behavior across eight critical risk categories.<n>Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms.<n>It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors.
  arXiv  Detail & Related papers  (2025-07-08T16:18:54Z)
• Agent-SafetyBench: Evaluating the Safety of LLM Agents [72.92604341646691]
  We introduce Agent-SafetyBench, a benchmark designed to evaluate the safety of large language models (LLMs)<n>Agent-SafetyBench encompasses 349 interaction environments and 2,000 test cases, evaluating 8 categories of safety risks and covering 10 common failure modes frequently encountered in unsafe interactions.<n>Our evaluation of 16 popular LLM agents reveals a concerning result: none of the agents achieves a safety score above 60%.
  arXiv  Detail & Related papers  (2024-12-19T02:35:15Z)
• Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training [67.30423823744506]
  We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position.<n>DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence.
  arXiv  Detail & Related papers  (2024-07-12T09:36:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.