Understanding the Effects of Safety Unalignment on Large Language Models

• URL: http://arxiv.org/abs/2604.02574v1
• Date: Thu, 02 Apr 2026 23:09:43 GMT
• Title: Understanding the Effects of Safety Unalignment on Large Language Models
• Abstract summary: We study the impact of unaligning six popular LLMs of various sizes across a large number of malicious and benign tasks.<n>In contrast to JT, the majority of WO unaligned models are far less prone to hallucinations, better retain their original natural-language performance, and are more effective at state-of-the-art adversarial and cyber attacks.
• Score: 0.5076419064097732
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment for deployed frontier models, two separate lines of recent work--jailbreak-tuning (JT) and weight orthogonalization (WO)--have shown that safety guardrails may be largely disabled, resulting in LLMs which comply with harmful requests they would normally refuse. In spite of far-reaching safety implications, analysis has largely been limited to refusal rates of each unalignment method in isolation, leaving their relative effects on adversarial LLM capabilities unknown. To fill this gap, we study the impact of unaligning six popular LLMs of various sizes across a large number of malicious and benign tasks, using both JT and WO. Across the evaluated models, we show that while refusal degradation is split between the two methods, WO produces LLMs far more capable of aiding in malicious activity; in contrast to JT, the majority of WO unaligned models are far less prone to hallucinations, better retain their original natural-language performance, and are more effective at state-of-the-art adversarial and cyber attacks. To thus help mitigate the malicious risks of WO unalignment, we conclude by showing that supervised fine-tuning effectively limits the adversarial attack abilities enabled by WO, without drastically affecting hallucination rates or natural language performance.

Related papers

• Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation [23.989016366701232]
  Large language models harbor safety vulnerabilities.<n>Improvements in model safety often come at the cost of severe over-refusal.<n>We propose MOSR, designed to mitigate over-refusal by intervening the safety representation of LLMs.
  arXiv  Detail & Related papers  (2025-11-24T11:38:53Z)
• SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks [29.963044242980345]
  Jailbreak attacks pose a serious threat to the safety of Large Language Models.<n>We propose SafeLLM, a novel unlearning-based defense framework.<n>We show that SafeLLM substantially reduces attack success rates while maintaining high general-purpose performance.
  arXiv  Detail & Related papers  (2025-08-21T02:39:14Z)
• ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks [61.06621533874629]
  In-context learning (ICL) has demonstrated remarkable success in large language models (LLMs)<n>In this paper, we propose, for the first time, the dual-learning hypothesis, which posits that LLMs simultaneously learn both the task-relevant latent concepts and backdoor latent concepts.<n>Motivated by these findings, we propose ICLShield, a defense mechanism that dynamically adjusts the concept preference ratio.
  arXiv  Detail & Related papers  (2025-07-02T03:09:20Z)
• LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning [61.594212398272184]
  Low-Rank Extrapolation (LoX) improves robustness against benign and malicious fine-tuning attacks.<n>LoX leads to 11% to 54% absolute reductions in attack success rates.
  arXiv  Detail & Related papers  (2025-06-18T16:30:02Z)
• Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models [50.89022445197919]
  Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs)<n>Recent research has revealed that LALMs remain vulnerable to harmful queries due to insufficient safety-alignment.
  arXiv  Detail & Related papers  (2025-05-26T08:25:25Z)
• Align in Depth: Defending Jailbreak Attacks via Progressive Answer Detoxification [17.500701903902094]
  Large Language Models (LLMs) are vulnerable to jailbreak attacks, which use crafted prompts to elicit toxic responses.<n>This paper proposes DEEPALIGN, a robust defense framework that fine-tunes LLMs to progressively detoxify generated content.
  arXiv  Detail & Related papers  (2025-03-14T08:32:12Z)
• Improving LLM Safety Alignment with Dual-Objective Optimization [81.98466438000086]
  Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks.<n>We propose an improved safety alignment that disentangles DPO objectives into two components: (1) robust refusal training, which encourages refusal even when partial unsafe generations are produced, and (2) targeted unlearning of harmful knowledge.
  arXiv  Detail & Related papers  (2025-03-05T18:01:05Z)
• Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models [8.024771725860127]
  Jailbreak attacks manipulate large language models into generating harmful content.<n>Jailbreak Antidote enables real-time adjustment of safety preferences by manipulating a sparse subset of the model's internal states.<n>Our analysis reveals that safety-related information in LLMs is sparsely distributed.
  arXiv  Detail & Related papers  (2024-10-03T08:34:17Z)
• Robust LLM safeguarding via refusal feature adversarial training [15.76605079209956]
  Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful responses.<n>We propose Refusal Feature Adrial Training (ReFAT), a novel algorithm that efficiently performs adversarial training.<n>Experiment results show that ReFAT significantly improves the robustness of three popular LLMs against a wide range of adversarial attacks.
  arXiv  Detail & Related papers  (2024-09-30T08:41:39Z)
• LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models [21.02295266675853]
  We propose a novel black-box jailbreak attack method, Analyzing-based Jailbreak (ABJ)<n>ABJ comprises two independent attack paths, which exploit the model's multimodal reasoning capabilities to bypass safety mechanisms.<n>Our work reveals a new type of safety risk and highlights the urgent need to mitigate implicit vulnerabilities in the model's reasoning process.
  arXiv  Detail & Related papers  (2024-07-23T06:14:41Z)
• 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)
• Visual Adversarial Examples Jailbreak Aligned Large Language Models [66.53468356460365]
  We show that the continuous and high-dimensional nature of the visual input makes it a weak link against adversarial attacks. We exploit visual adversarial examples to circumvent the safety guardrail of aligned LLMs with integrated vision. Our study underscores the escalating adversarial risks associated with the pursuit of multimodality.
  arXiv  Detail & Related papers  (2023-06-22T22:13:03Z)

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.