Related papers: BAIT: Boundary-Guided Disclosure Escalation via Se…

Conversational large language models are trained to refuse to answer harmful questions. However, emergent jailbreaking techniques can still elicit unsafe outputs, presenting an ongoing challenge for model alignment. To better understand how…

Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under adversarial attacks. Existing alignment methods attempt to…

Despite rigorous safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive trials, lacking mechanistic interpretability and query…

Binary vulnerability analysis is increasingly performed by LLM-based agents in an iterative, multi-pass manner, with the model as the core decision-maker. However, how such systems organize exploration over hundreds of reasoning steps…

With the prevalence of mobile data visualizations, there have been growing concerns about their privacy risks, especially shoulder surfing attacks. Inspired by prior research on visual illusion, we propose BAIT, a novel approach to…

While recent advancements in large language model (LLM) alignment have enabled the effective identification of malicious objectives involving scene nesting and keyword rewriting, our study reveals that these methods remain inadequate at…

Large Language Models (LLMs) remain vulnerable to jailbreak attacks, where adversarially crafted prompts induce policy-violating responses despite safety alignment. Existing defenses typically improve safety through external filtering,…

Large-scale self-supervised models have recently revolutionized our ability to perform a variety of tasks within the vision and language domains. However, using such models for autonomous systems is challenging because of safety…

Despite extensive safety measures, LLMs are vulnerable to adversarial inputs, or jailbreaks, which can elicit unsafe behaviors. In this work, we introduce bijection learning, a powerful attack algorithm which automatically fuzzes LLMs for…

Jailbreaking large language models (LLMs) has emerged as a critical security challenge with the widespread deployment of conversational AI systems. Adversarial users exploit these models through carefully crafted prompts to elicit…

The remarkable capabilities of Large Language Models (LLMs) have raised significant safety concerns, particularly regarding "jailbreak" attacks that exploit adversarial prompts to bypass safety alignment mechanisms. Existing defense…

Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulnerability in which the previous response in the dialogue can…

Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer.…

Autoregressive Sequence-To-Sequence models are the foundation of many Deep Learning achievements in major research fields such as Vision and Natural Language Processing. Despite that, they still present significant limitations. For…

Progress in many task domains emerges from repeated revisions to previous solution attempts. Training agents that can reliably self-improve over such sequences at inference-time is a natural target for reinforcement learning (RL), yet the…

By integrating Chain-of-Thought(CoT) reasoning, Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, particularly by improving generalization and interpretability. However, the security of…

Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, the practical effectiveness of existing attacks is undermined…

Deep iterative chain-of-thought (CoT) reasoning enables LLMs to tackle complex tasks by progressively activating relevant pre-trained knowledge. However, it faces challenges in ensuring continual improvement and determining a stopping…

Multi-turn jailbreak attacks simulate real-world human interactions by engaging large language models (LLMs) in iterative dialogues, exposing critical safety vulnerabilities. However, existing methods often struggle to balance semantic…

To demonstrate and address the underlying maliciousness, we propose a theoretical hypothesis and analytical approach, and introduce a new black-box jailbreak attack methodology named IntentObfuscator, exploiting this identified flaw by…