Related papers: E$^2$AT: Multimodal Jailbreak Defense via Dynamic …
Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the…
Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a…
Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal and adversarial…
Text-to-image (T2I) models commonly incorporate defense mechanisms to prevent the generation of sensitive images. Unfortunately, recent jailbreak attacks have shown that adversarial prompts can effectively bypass these mechanisms and induce…
Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores…
Despite the remarkable versatility of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) to generalize across both language and vision tasks, LLMs and MLLMs have shown vulnerability to jailbreaking, generating textual outputs that…
The release of open-weight large language models (LLMs) creates a tension between advancing accessible research and preventing misuse, such as malicious fine-tuning to elicit harmful content. Current safety measures struggle to preserve the…
Optimization methods are widely employed in deep learning to identify and mitigate undesired model responses. While gradient-based techniques have proven effective for image models, their application to language models is hindered by the…
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks. Nevertheless, they still pose notable safety risks due to potential misuse for malicious purposes. Jailbreaking, which seeks to induce models to…
Multi-turn jailbreak attacks simulate real-world human interactions by engaging large language models (LLMs) in iterative dialogues, exposing critical safety vulnerabilities. However, existing methods often struggle to balance semantic…
The explosive growth of multimodal data has driven the rapid development of multimodal entity linking (MEL) models. However, existing studies have not systematically investigated the impact of visual adversarial attacks on MEL models. We…
The attack surface of a multimodal large language model (MLLM) is language-dependent in ways that reveal the mechanistic structure of alignment failures. We present the first systematic cross-lingual, multimodal red-teaming study comparing…
Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual question answering and audio translation. While powerful, this…
Despite the implementation of safety alignment strategies, large language models (LLMs) remain vulnerable to jailbreak attacks, which undermine these safety guardrails and pose significant security threats. Some defenses have been proposed…
The widespread application of large VLMs makes ensuring their secure deployment critical. While recent studies have demonstrated jailbreak attacks on VLMs, existing approaches are limited: they require either white-box access, restricting…
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.…
Recent advancements in large audio-language models (LALMs) have enabled speech-based user interactions, significantly enhancing user experience and accelerating the deployment of LALMs in real-world applications. However, ensuring the…
While significant attention has been dedicated to exploiting weaknesses in LLMs through jailbreaking attacks, there remains a paucity of effort in defending against these attacks. We point out a pivotal factor contributing to the success of…
Despite recent efforts in Large Language Model (LLM) safety and alignment, current adversarial attacks on frontier LLMs can still consistently force harmful generations. Although adversarial training has been widely studied and shown to…
Recent research has focused on exploring the vulnerabilities of Large Language Models (LLMs), aiming to elicit harmful and/or sensitive content from LLMs. However, due to the insufficient research on dual-jailbreaking -- attacks targeting…