Related papers: Multi-Turn Adaptive Prompting Attack on Large Visi…
Large language models (LLMs) have exhibited outstanding performance in engaging with humans and addressing complex questions by leveraging their vast implicit knowledge and robust reasoning capabilities. However, such models are vulnerable…
The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol…
Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is important to anticipate the range of potential Jailbreak attacks…
Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…
Intent-obfuscation-based jailbreak attacks on multimodal large language models (MLLMs) transform a harmful query into a concealed multimodal input to bypass safety mechanisms. We show that such attacks are governed by a…
Safety-aligned LLMs suffer from two failure modes: jailbreak (answering harmful inputs) and over-refusal (declining benign queries). Existing vector steering methods adjust the magnitude of answer vectors, but this creates a fundamental…
The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesirable ways. In this work, we focus on a popular class of…
Large language models (LLMs) are susceptible to social-engineered attacks that are human-interpretable but require a high level of comprehension for LLMs to counteract. Existing defensive measures can only mitigate less than half of these…
While Large Language Models (LLMs) display versatile functionality, they continue to generate harmful, biased, and toxic content, as demonstrated by the prevalence of human-designed jailbreaks. In this work, we present Tree of Attacks with…
Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…
We discuss the ``Infinitely Many Paraphrases'' attacks (IMP), a category of jailbreaks that leverages the increasing capabilities of a model to handle paraphrases and encoded communications to bypass their defensive mechanisms. IMPs'…
As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…
Large Language Diffusion Models (LLDMs) exhibit comparable performance to LLMs while offering distinct advantages in inference speed and mathematical reasoning tasks.The precise and rapid generation capabilities of LLDMs amplify concerns of…
Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment. This has led to the task of training automated multi-turn attackers to probe model safety…
Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…
Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…
Jailbreak attacks reveal critical vulnerabilities in Large Language Models (LLMs) by causing them to generate harmful or unethical content. Evaluating these threats is particularly challenging due to the evolving nature of LLMs and the…
Multimodal large language models (MLLMs) are widely used in vision-language reasoning tasks. However, their vulnerability to adversarial prompts remains a serious concern, as safety mechanisms often fail to prevent the generation of harmful…
The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts. While existing research primarily…
Text-to-Image models may generate harmful content, such as pornographic images, particularly when unsafe prompts are submitted. To address this issue, safety filters are often added on top of text-to-image models, or the models themselves…