Skip to content
Log in

Similar papers

Preprint Jul 2026

Safety Targeted Embedding Exploit via Refinement

Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training. To study this phenomenon, we introduce STEER (Safety Targeted Embedding Exploit via Refinement), a gradient-guided attack that identifies words contributing most strongly to the model's refusal behavior and iteratively translates them into low-resource languages to suppress refusal while preserving harmful intent. Across six open-source 8B-parameter models, STEER achieves attack success rates of up to 93.0% on JailbreakBench and 96.7% on AdvBench, outperforming random code-switching and Greedy Coordinate Gradient (GCG). The resulting prompts also transfer to GPT-4o-mini, achieving a 35.5% attack success rate without requiring access to the target model, suggesting that the underlying weakness is not specific to a single architecture. These findings demonstrate that safety mechanisms aligned primarily on English cannot be assumed to generalize across multilingual inputs. We argue that improving multilingual safety requires broader coverage during alignment and mechanisms that explicitly detect and abstain on out-of-distribution inputs.

Joshua Adrian Cahyono · 0 citations

Explaining Jailbreaks: Structured and Interpretable Safety Assessment for Large Language Models

This work proposes an explanation-aware safety framework that augments binary harmfulness detection with structured, human-interpretable explanations capturing severity, strategies, trigger spans, ratio-nales, and derived safety factors, and introduces a human–LLM hybrid annotation and canonicaliza-tion pipeline.

Sunghee Dong, Sungwon Yi, Kangmin Bae et al. · 0 citations
Review Open access Aug 2026

Recent Advances and Open Challenges in Mitigating Inference-Time Attacks on Large Language Models

A defense taxonomy spanning three axes, namely prompt-level, inference-time, and training-time interventions, is proposed, within which 30 mitigation mechanisms published from 2024 onwards are systematically analyzed, demonstrating that no single defense mechanism provides comprehensive protection, and that robust deployment mandates layered, complementary strategies.

Berkay Özçam, Mustafa Kara, Muhammet Ali Aydin et al. · 0 citations
Review Open access 2026

DeepSeek Under Attack: An Analysis of Jailbreak Attacks and Prompt-Level Defenses

The reasoning model DeepSeek-R1 was more susceptible to jailbreak attacks than the non-reasoning model DeepSeek-V3, and different prompt-level defenses were effective against static jailbreaks.

V. T. Hayashi, Milton Pedro Pagliuso Neto, C. Miers et al. · 0 citations
Open access Jul 2026

TSA: A Two-Stage Jailbreak Attack Exploiting Logical Consistency of Large Language Models

The findings suggest that such logical-consistency-based vulnerability may exist among the tested mainstream LLMs, highlighting the necessity to optimize safety alignment for defending against this category of reasoning-driven jailbreak attacks.

Yiming Du, Wenjuan Lian, Hongbao Zhang et al. · 0 citations