SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement
Despite the significant efforts devoted to aligning large language models (LLMs) with human values and ensuring safe deployment, recent work has revealed that LLMs remain vulnerable to adversarial jailbreak attacks that can bypass safety guardrails and elicit harmful responses. Many defense methods are proposed to detect jailbreaks but they are limited in their effectiveness to counter wide-range optimization-based jailbreak mechanisms that can yield highly fluency-optimized or harmful semantic obfuscated prompts. To tackle this challenge, we propose a unified detection framework SAFEGuard which incorporates a hybrid fluency measurement based on cross-layer distribution distance and perpl...
| Authors | Quoc Viet Vo, Trung Le, Damith C. Ranasinghe et al. |
|---|---|
| Primary category | cs.LG |
| Published | 5 September 2026 |
| Last updated at source | 5 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.