Related papers: Retrieval-Augmented Defense: Adaptive and Controll…

The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…

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…

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm to enhance large language models (LLMs) with external knowledge, reducing hallucinations and compensating for outdated information. However, recent studies have…

Large language models (LLMs) are inherently vulnerable to unintended privacy breaches. Consequently, systematic red-teaming research is essential for developing robust defense mechanisms. However, current data extraction methods suffer from…

Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representation shifts associated with jailbreak success, but they leave a more fundamental question…

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

The systems and software powered by Large Language Models (LLMs) and Multi-Modal LLMs (MLLMs) have played a critical role in numerous scenarios. However, current LLM systems are vulnerable to prompt-based attacks, with jailbreaking attacks…

Jailbreak attacks pose significant threats to large language models (LLMs), enabling attackers to bypass safeguards. However, existing reactive defense approaches struggle to keep up with the rapidly evolving multi-turn jailbreaks, where…

Large language models (LLMs) remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry,…

As the use of large language models (LLMs) continues to expand, ensuring their safety and robustness has become a critical challenge. In particular, jailbreak attacks that bypass built-in safety mechanisms are increasingly recognized as a…

Safety, security, and compliance are essential requirements when aligning large language models (LLMs). However, many seemingly aligned LLMs are soon shown to be susceptible to jailbreak attacks. These attacks aim to circumvent the models'…

Parametric language models (LMs), which are trained on vast amounts of web data, exhibit remarkable flexibility and capability. However, they still face practical challenges such as hallucinations, difficulty in adapting to new data…

Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attacks. Existing defenses predominantly rely on safety…

Despite extensive safety alignment, Large Language Models (LLMs) often fail against jailbreak attacks. While machine unlearning has emerged as a promising defense by erasing specific harmful parameters, current methods remain vulnerable to…

Assessing the safety of autonomous driving policy is of great importance, and reinforcement learning (RL) has emerged as a powerful method for discovering critical vulnerabilities in driving policies. However, existing RL-based approaches…

Diffusion models (DMs) have recently demonstrated remarkable generation capability. However, their training generally requires huge computational resources and large-scale datasets. To solve these, recent studies empower DMs with the…

Retrieval-augmented generation (RAG) systems are increasingly deployed in sensitive domains such as healthcare and law, where they rely on private, domain-specific knowledge. This capability introduces significant security risks, including…

Recently, Large Language Model (LLM)-empowered recommender systems have revolutionized personalized recommendation frameworks and attracted extensive attention. Despite the remarkable success, existing LLM-empowered RecSys have been…

Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that disguise malicious intent through role-play scenarios,…

Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention. However, even the most advanced LLMs face challenges such as hallucinations and real-time updating of their knowledge.…