Understanding the Effects of Safety Unalignment on Large Language Models

Computer Science > Cryptography and Security [Submitted on 2 Apr 2026] Understanding the Effects of Safety Unalignment on Large Language Models John T. Halloran 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. Comments: 12 pages, 2 figures, 5 tables Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2604.02574 [cs.CR]   (or arXiv:2604.02574v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.02574 Focus to learn more Submission history From: John Halloran [view email] [v1] Thu, 2 Apr 2026 23:09:43 UTC (41 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.AI cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)