Related papers: Jailbreaking the Matrix: Nullspace Steering for Co…
Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representation shifts associated with jailbreak success, but they leave a more fundamental question…
As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.…
Recent advancements in AI safety have led to increased efforts in training and red-teaming large language models (LLMs) to mitigate unsafe content generation. However, these safety mechanisms may not be comprehensive, leaving potential…
Multimodal Large Language Models (MLLMs) have achieved impressive performance and have been put into practical use in commercial applications, but they still have potential safety mechanism vulnerabilities. Jailbreak attacks are red teaming…
Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…
Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue,…
Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…
Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…
While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after…
Jailbreaking large language models (LLMs) has emerged as a pressing concern with the increasing prevalence and accessibility of conversational LLMs. Adversarial users often exploit these models through carefully engineered prompts to elicit…
Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…
Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video (T2V) models typically add adversarial perturbations to obviously unsafe prompts, which are often easy to detect and…
Large language models (LLMs) are widely applied in various fields of society due to their powerful reasoning, understanding, and generation capabilities. However, the security issues associated with these models are becoming increasingly…
Large language models (LLMs) often encode cognitive behaviors unpredictably across prompts, layers, and contexts, making them difficult to diagnose and control. We present CBMAS, a diagnostic framework for continuous activation steering,…
Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…
Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety alignment and elicit harmful responses. A growing body of work shows that contextual priming, where earlier turns covertly bias later replies,…
In this paper, we investigate the safety mechanisms of instruction fine-tuned large language models (LLMs). We discover that re-weighting MLP neurons can significantly compromise a model's safety, especially for MLPs in end-of-sentence…
Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs). A considerable amount of research exists proposing more effective jailbreak attacks, including the…
Despite their impressive capabilities, Large Language Models (LLMs) exhibit unwanted uncertainty, a phenomenon where a model changes a previously correct answer into an incorrect one when re-prompted. This behavior undermines trust and…
Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream black-box jailbreak attacks on VLMs work by distributing…