Related papers: Beyond Attack Success Rate: Temporal Logit Observa…

Vision Language Models (VLMs) can produce unintended and harmful content when exposed to adversarial attacks, particularly because their vision capabilities create new vulnerabilities. Existing defenses, such as input preprocessing,…

Large language models (LLMs) can be prompted with specific styles (e.g., formatting responses as lists), including in malicious queries. Prior jailbreak research mainly augments these queries with additional string transformations to…

We introduce \emph{self-jailbreaking}, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which often rely on handcrafted prompts or separate attacker models, self-jailbreaking requires no…

Jailbreak attacks designed to bypass safety mechanisms pose a serious threat by prompting LLMs to generate harmful or inappropriate content, despite alignment with ethical guidelines. Crafting universal filtering rules remains difficult due…

Large Language Models (LLMs) deploy safety mechanisms to prevent harmful outputs, yet these defenses remain vulnerable to adversarial prompts. While existing research demonstrates that jailbreak attacks succeed, it does not explain…

LLM-based multi-agent systems are increasingly deployed for payment workflows, yet prevailing metrics, Task Success Rate (TSR) and Agent Handoff F1-Score (HF1), capture only final outcomes or unordered routing decisions. We introduce the…

Air Traffic Control (ATC) is a safety-critical domain in which incorrect interpretation of instructions may lead to severe operational consequences. While large language models (LLMs) demonstrate strong general performance, their…

In this paper, we introduce a formal notion of partial compliance, called Attack-resistance, of a computer program running together with a defense mechanism w.r.t a non-exploitability specification. In our setting, a program may contain…

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

Defending against jailbreak attacks is crucial for the safe deployment of Large Language Models (LLMs). Recent research has attempted to improve safety by training models to reason over safety rules before responding. However, a key issue…

Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulnerable to jailbreak attacks that bypass safety guardrails.…

Thinking mode has always been regarded as one of the most valuable modes in LLMs. However, we uncover a surprising and previously overlooked phenomenon: LLMs with thinking mode are more easily broken by Jailbreak attack. We evaluate 9 LLMs…

Think-with-image reasoning is emerging as a new inference paradigm for large vision-language models, but its safety implications remain poorly understood. Existing systems already span multiple process designs, including direct response…

As large language models (LLMs) become increasingly deployed in safety-critical applications, the lack of systematic methods to assess their vulnerability to jailbreak attacks presents a critical security gap. We introduce the jailbreak…

LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing…

LLM jailbreaks are a widespread safety challenge. Given this problem has not yet been tractable, we suggest targeting a key failure mechanism: the failure of safety to generalize across semantically equivalent inputs. We further focus the…

Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning. However, CoT is not always faithful to the model's final output, undermining its reliability as a monitoring…

Jailbreak attacks represent one of the most sophisticated threats to the security of large language models (LLMs). To deal with such risks, we introduce an innovative framework that can help evaluate the effectiveness of jailbreak attacks…

Large language models (LLMs) have gained widespread recognition for their superior comprehension and have been deployed across numerous domains. Building on Chain-of-Thought (CoT) ideology, Large Reasoning models (LRMs) further exhibit…

Large Language Models (LLMs) are increasingly exposed to adaptive jailbreaking, particularly in high-stakes Chemical, Biological, Radiological, and Nuclear (CBRN) domains. Although streaming probes enable real-time monitoring, they still…