arXiv · 2611.18601
Jailbreak LLMs with Linguistic Style as a Hidden Attack Surface
Abstract
We show that linguistic style is a systematic and previously overlooked attack surface for LLM safety. Across a diverse taxonomy of styles and multiple state-of-the-art models, stylistic rewrites of identical harmful goals produce order-of-magnitude differences in Attack Success Rate (ASR), with some styles achieving up to 80\% ASR while others remain below 6\%. To exploit this vulnerability, we introduce a lightweight single-pass attack framework that combines a style-conditioned generator with a BERT-based style selector, achieving performance competitive with substantially more expensive multi-turn optimization methods. To understand why style affects safety behavior, we conduct mechanistic analysis on LLaMA-3.1-8B and find that stylistic rewrites disrupt refusal representations while preserving recoverable harmful intent, suggesting a distributed failure mode rather than a single refusal mechanism. Motivated by this finding, we develop a style-aware Direct Preference Optimization defense that reduces ASR from 86\% to 19.5\% while largely preserving utility. Together, our results establish linguistic style as a critical factor in adversarial robustness and provide both mechanistic insight and a practical defense.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Priyanshu Mohanty, Sarthakbrata Halder, Srikant Panda, Afshin Oroojlooy, Murari Mandal. 2026-09-01. Jailbreak LLMs with Linguistic Style as a Hidden Attack Surface. https://searcharxiv.com/abs/2611.18601
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.