相关论文: PBI-Attack: Prior-Guided Bimodal Interactive Black…

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) have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal…

Jailbreak attacks on multimodal AI systems remain underexplored, even though unsafe image generation can have more severe consequences than unsafe text and current defenses are relatively immature. We introduce PAST2HARM, a simple yet…

We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than…

Large Vision-Language Models (LVLMs) have shown significant progress in responding well to visual-instructions from users. However, these instructions, encompassing images and text, are susceptible to both intentional and inadvertent…

As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone and an expanded attack surface. SLMs have been previously shown to be susceptible to jailbreaking, where…

The proliferation of large language models (LLMs) has underscored concerns regarding their security vulnerabilities, notably against jailbreak attacks, where adversaries design jailbreak prompts to circumvent safety mechanisms for potential…

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…

Vision-Language Models (VLMs) have achieved impressive progress in multimodal text generation, yet their rapid adoption raises increasing concerns about security vulnerabilities. Existing backdoor attacks against VLMs primarily rely on…

The widespread deployment of large language models (LLMs) has raised growing concerns about their misuse risks and associated safety issues. While prior studies have examined the safety of LLMs in general usage, code generation, and…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Large Vision-Language Models (LVLMs) signify a groundbreaking paradigm shift within the Artificial Intelligence (AI) community, extending beyond the capabilities of Large Language Models (LLMs) by assimilating additional modalities (e.g.,…

We have uncovered a powerful jailbreak technique that leverages large language models' ability to diverge from prior context, enabling them to bypass safety constraints and generate harmful outputs. By simply instructing the LLM to deviate…

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…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety…

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…

Modern large language model (LLM) developers typically conduct a safety alignment to prevent an LLM from generating unethical or harmful content. Recent studies have discovered that the safety alignment of LLMs can be bypassed by…

Recent advances in Vision-Language Models (VLMs) facilitate a new class of embodied AI systems, where these models are integrated into physical platforms, e.g. robots and autonomous vehicles, to interpret visual scenes and execute natural…

Aligning large language models (LLMs) with human values, particularly when facing complex and stealthy jailbreak attacks, presents a formidable challenge. Unfortunately, existing methods often overlook this intrinsic nature of jailbreaks,…