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

Large Language Model Vulnerabilities

Do LLMs Know Their Vulnerable Scenarios?

Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards. Existing red-teaming methods empirically identify effective scenarios through observed attack outcomes, but why particular scenarios weaken refusal remains mechanistically unclear. Meanwhile, mechanistic interpretability studies have characterized both refusal directions and jailbreak-associated features, without explaining the relationship between the two representations. In this work, we show that scenario-wrapped prompts activate internal scenario directions whose causal steering consistently reduces refusal scores. Building on this finding, we propose \textsc{Concept2Scenario}, a concept-based attribution framework for vulnerable scenario discovery. It instantiates a broad concept space with a sparse autoencoder, attributes refusal suppression to individual concepts, translates the identified concepts into interpretable natural-language scenarios, and identifies synergistic scenario combinations through interaction attribution. Across three open-source models, two safety benchmarks, and six black-box jailbreak methods, the discovered scenarios serve as reusable priors that improve average attack success rates by up to $18.2$ percentage points. They also transfer to GPT-5, Claude-Haiku-4.5, and Gemini-3-Flash, suggesting that some scenario-level refusal vulnerabilities are shared across model families. Moreover, the identified combinations outperform their individual constituents and enable iterative attacks to succeed in fewer turns.

MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak Vulnerabilities

Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet how different factors shape their jailbreak vulnerabilities remains poorly understood. Existing benchmarks often couple harmful intent, prompt framing, visual semantics, and instruction carrier within individual jailbreak instances, obscuring the specific sources of observed vulnerabilities. To address this limitation, we introduce MMJailBench, a factorized benchmark that systematically varies and combines these factors under controlled configurations, enabling fine-grained comparison and factor-level attribution. Large-scale evaluations across 16 open-weight and proprietary MLLMs reveal highly heterogeneous and model-dependent vulnerability profiles. Jailbreak vulnerability varies markedly across harm domains, exposing uneven coverage in current multimodal safety alignment. Prompt framing emerges as the dominant source of variation, task-relevant visual semantics systematically increase jailbreak susceptibility with authority-like cues exposing particularly pronounced vulnerabilities, and visually rendered instructions do not consistently increase jailbreak susceptibility relative to direct textual instructions. To further investigate the risks introduced by multimodal context, we conduct diagnostic analyses on a representative open-weight model and identify vulnerability-associated patterns in internal representations and cross-modal interactions. Finally, we develop a modular multimodal jailbreak evaluation suite with full and lightweight configurations, multiple judge options, and multidimensional metrics, enabling reproducible, scalable, and cost-efficient multimodal jailbreak auditing.

HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models

Experiments across three instruction-tuned models show that HiRoute achieves high safety rates across multiple safety benchmarks while preserving safe-response helpfulness, reducing over-refusal, and maintaining competitive performance on general-purpose tasks.

IC-GCG: Jailbreaking Large Language Models via Intermediate Consistency Optimization

Recent jailbreak attacks demonstrate that large language models (LLMs) can be manipulated to generate harmful outputs through adversarial prompts even after robust alignment. However, prevailing methods typically focus on forcing a desired response at the output layer—a surface-level strategy that is brittle and often fails to bypass the more fundamental safety checks embedded within the model’s internal mechanisms. In contrast, we propose intermediate consistency greedy coordinate gradient (IC-GCG), an approach that extends the GCG framework to explicitly target the model’s internal alignment mechanism. Our method forces a harmful prompt’s hidden representations to mimic those of a semantically related benign counterpart within critical middle layers. By adapting a greedy coordinate optimization strategy to craft an adversarial suffix that minimizes this representational distance, IC-GCG creates “semantic camouflag” that bypasses the model’s internal safety judgments. Experiments on several aligned LLMs indicate that IC-GCG substantially outperforms state-of-the-art baselines, increasing the average attack success rate to 94.3% and proving particularly effective against strongly aligned models such as LLAMA2-7B-CHAT, where it boosts success by over 56 percentage points. Furthermore, the resulting suffixes display superior transferability to other models. Ablation studies confirm that this high efficacy critically depends on a strong semantic link between the harmful and benign prompt pair, empirically validating that the integrity of intermediate representations is a crucial vulnerability and highlighting the need for a new class of defenses that operate directly on the model’s internal states.

Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety

It is shown that English-only safety evaluations are insufficient; they require accounting for script family, perturbation type, and per-language alignment coverage, and a geometric mechanistic analysis of refusal failure across language tiers.