Related papers: Circumventing Safety Alignment in Large Language M…
Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content, restricting their safe deployment. While traditional methods (e.g., alignment) adjust output preferences, they fail to…
Backdoor Attacks have been a serious vulnerability against Large Language Models (LLMs). However, previous methods only reveal such risk in specific models, or present tasks transferability after attacking the pre-trained phase. So, how…
Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…
Advanced Persistent Threats (APTs) pose a major cybersecurity challenge due to their stealth and ability to mimic normal system behavior, making detection particularly difficult in highly imbalanced datasets. Traditional anomaly detection…
Large Language Models (LLMs) have been extensively used across diverse domains, including virtual assistants, automated code generation, and scientific research. However, they remain vulnerable to jailbreak attacks, which manipulate the…
Large Language Models (LLMs) drive current AI breakthroughs despite very little being known about their internal representations. In this work, we propose to shed the light on LLMs inner mechanisms through the lens of geometry. In…
The existing safety alignment of Large Language Models (LLMs) is found fragile and could be easily attacked through different strategies, such as through fine-tuning on a few harmful examples or manipulating the prefix of the generation…
Large Language Models (LLMs) have revolutionized natural language processing, but their robustness against adversarial attacks remains a critical concern. We presents a novel white-box style attack approach that exposes vulnerabilities in…
Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense of overcautious behavior, leading models to incorrectly…
Detecting life-threatening language is essential for safeguarding individuals in distress, promoting mental health and well-being, and preventing potential harm and loss of life. This paper presents an effective approach to identifying…
This paper studies the vulnerabilities of transformer-based Large Language Models (LLMs) to jailbreaking attacks, focusing specifically on the optimization-based Greedy Coordinate Gradient (GCG) strategy. We first observe a positive…
Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior of machine learning…
Recently, Large Language Models (LLMs) have made significant advancements and are now widely used across various domains. Unfortunately, there has been a rising concern that LLMs can be misused to generate harmful or malicious content.…
Large Language Models (LLMs) generating unsafe responses to toxic prompts is a significant issue in their applications. While various efforts aim to address this safety concern, previous approaches often demand substantial human data…
Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…
Improving the safety and reliability of large language models (LLMs) is a crucial aspect of realizing trustworthy AI systems. Although alignment methods aim to suppress harmful content generation, LLMs are often still vulnerable to…
Recent work discovered Emergent Misalignment (EM): fine-tuning large language models on narrowly harmful datasets can lead them to become broadly misaligned. A survey of experts prior to publication revealed this was highly unexpected,…
Typographic prompt injection exploits vision language models' (VLMs) ability to read text rendered in images, posing a growing threat as VLMs power autonomous agents. Prior work typically focus on maximizing attack success rate (ASR) but…
Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs…
The safety alignment of large language models (LLMs) is becoming increasingly important with their democratization. In this paper, we study the safety degradation that comes with adapting LLMs to new tasks. We attribute this safety…