Related papers: Visual-RolePlay: Universal Jailbreak Attack on Mul…
While multimodal large language models (MLLMs) have achieved remarkable success in recent advancements, their susceptibility to jailbreak attacks has come to light. In such attacks, adversaries exploit carefully crafted prompts to coerce…
The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabilities in real-world settings. Without a principled objective for gradient-based optimization,…
Large language models (LLMs) have seen rapid development in recent years, revolutionizing various applications and significantly enhancing convenience and productivity. However, alongside their impressive capabilities, ethical concerns and…
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…
Multi-modal large language models (MLLMs), capable of processing text, images, and audio, have been widely adopted in various AI applications. However, recent MLLMs integrating images and text remain highly vulnerable to coordinated…
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…
Despite the rapid progress of Large Vision-Language Models (LVLMs), the integration of visual modalities introduces new safety vulnerabilities that adversaries can exploit to elicit biased or malicious outputs. In this paper, we demonstrate…
Large language models (LLMs) have demonstrated remarkable capabilities, but their power comes with significant security considerations. While extensive research has been conducted on the safety of LLMs in chat mode, the security…
Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…
Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…
With the rapid advancement of multimodal large language models (MLLMs), concerns regarding their security have increasingly captured the attention of both academia and industry. Although MLLMs are vulnerable to jailbreak attacks, designing…
Large Vision-Language Models (LVLMs), trained on multimodal big datasets, have significantly advanced AI by excelling in vision-language tasks. However, these models remain vulnerable to adversarial attacks, particularly jailbreak attacks,…
Large Language Models (LLMs) demonstrate impressive zero-shot performance across a wide range of natural language processing tasks. Integrating various modality encoders further expands their capabilities, giving rise to Multimodal Large…
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 Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning content. However, exposing a model's internal reasoning process introduces additional…
With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), the imperative to ensure their safety has become increasingly pronounced. However, with the integration of additional modalities, MLLMs are exposed to…
Large Language Models (LLMs) are widely used in natural language processing but face the risk of jailbreak attacks that maliciously induce them to generate harmful content. Existing jailbreak attacks, including character-level and…
We explore visual prompt injection (VPI) that maliciously exploits the ability of large vision-language models (LVLMs) to follow instructions drawn onto the input image. We propose a new VPI method, "goal hijacking via visual prompt…
Existing adversarial attacks for VLP models are mostly sample-specific, resulting in substantial computational overhead when scaled to large datasets or new scenarios. To overcome this limitation, we propose Hierarchical Refinement Attack…
Multi-Modal Language Models (MLLMs) have transformed artificial intelligence by combining visual and text data, making applications like image captioning, visual question answering, and multi-modal content creation possible. This ability to…