Related papers: Mitigating Many-Shot Jailbreaking
Recent advances in Multimodal Large Language Models (MLLMs) have significantly enhanced the naturalness and flexibility of human computer interaction by enabling seamless understanding across text, vision, and audio modalities. Among these,…
Large Language Models (LLMs), used in creative writing, code generation, and translation, generate text based on input sequences but are vulnerable to jailbreak attacks, where crafted prompts induce harmful outputs. Most jailbreak prompt…
With the enhanced performance of large models on natural language processing tasks, potential moral and ethical issues of large models arise. There exist malicious attackers who induce large models to jailbreak and generate information…
Large language models (LLMs) are improving at an exceptional rate. However, these models are still susceptible to jailbreak attacks, which are becoming increasingly dangerous as models become increasingly powerful. In this work, we…
Large Language Models (LLMs) are a double-edged sword capable of generating harmful misinformation -- inadvertently, or when prompted by "jailbreak" attacks that attempt to produce malicious outputs. LLMs could, with additional research, be…
The widespread adoption of thinking mode in large language models (LLMs) has significantly enhanced complex task processing capabilities while introducing new security risks. When subjected to jailbreak attacks, the step-by-step reasoning…
Jailbreak attacks against large language models (LLMs) aim to induce harmful behaviors in LLMs through carefully crafted adversarial prompts. To mitigate attacks, one way is to perform adversarial training (AT)-based alignment, i.e.,…
As large language models (LLMs) become more integral to society and technology, ensuring their safety becomes essential. Jailbreak attacks exploit vulnerabilities to bypass safety guardrails, posing a significant threat. However, the…
Recently, Multimodal Large Language Models (MLLMs) have demonstrated their superior ability in understanding multimodal content. However, they remain vulnerable to jailbreak attacks, which exploit weaknesses in their safety alignment to…
The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed…
Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly…
Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…
Jailbreaking in Large Language Models (LLMs) is a major security concern as it can deceive LLMs to generate harmful text. Yet, there is still insufficient understanding of how jailbreaking works, which makes it hard to develop effective…
Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks and defenses exist, their cross-lingual generalization…
While safety mechanisms have significantly progressed in filtering harmful text inputs, MLLMs remain vulnerable to multimodal jailbreaks that exploit their cross-modal reasoning capabilities. We present MIRAGE, a novel multimodal jailbreak…
Augmenting Large Language Models (LLMs) with image-understanding capabilities has resulted in a boom of high-performing Vision-Language models (VLMs). While studying the alignment of LLMs to human values has received widespread attention,…
LLMs are increasingly equipped with safety alignment mechanisms, yet recent studies demonstrate that they remain vulnerable to jailbreaking attacks that elicit harmful behaviors without explicit policy violations. While a growing body of…
Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, LLMs still tend to generate harmful responses when faced with malicious instructions, a phenomenon referred to as "Jailbreak…
Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts. Existing methods rely on discrete optimization or trained adversarial generators, but are slow,…
Large Language Models (LLMs) have exhibited remarkable capabilities but remain vulnerable to jailbreaking attacks, which can elicit harmful content from the models by manipulating the input prompts. Existing black-box jailbreaking…