Related papers: E$^2$AT: Multimodal Jailbreak Defense via Dynamic …

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…

While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after…

Multimodal Large Language Models (MLLMs) bridge the gap between visual and textual data, enabling a range of advanced applications. However, complex internal interactions among visual elements and their alignment with text can introduce…

Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt jailbreaking attacks involve adversaries crafting sophisticated prompts to elicit responses from…

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial attacks generate…

As LLMs gain stronger reasoning capabilities, their extended chain-of-thought introduces new degrees of complexity for defending against adversarial jailbreaks and prompt injection. We study consistency training, a family of fine-tuning…

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…

Multimodal Large Language Models (MLLMs), built upon LLMs, have recently gained attention for their capabilities in image recognition and understanding. However, while MLLMs are vulnerable to adversarial attacks, the transferability of…

Deep learning models have shown considerable vulnerability to adversarial attacks, particularly as attacker strategies become more sophisticated. While traditional adversarial training (AT) techniques offer some resilience, they often focus…

Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer.…

Deep Metric Learning (DML) has shown remarkable successes in many domains by taking advantage of powerful deep neural networks. Deep neural networks are prone to adversarial attacks and could be easily fooled by adversarial examples. The…

The study of large language models (LLMs) is a key area in open-world machine learning. Although LLMs demonstrate remarkable natural language processing capabilities, they also face several challenges, including consistency issues,…

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…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential, yet they face two major challenges: generalization and…

Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass safeguards with crafted input prompts, play a central role in…

We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

The use of Large Language Models (LLMs) as automatic judges for code evaluation is becoming increasingly prevalent in academic environments. But their reliability can be compromised by students who may employ adversarial prompting…

GPT-4V has attracted considerable attention due to its extraordinary capacity for integrating and processing multimodal information. At the same time, its ability of face recognition raises new safety concerns of privacy leakage. Despite…

Safety alignment in large language models (LLMs) is increasingly compromised by jailbreak attacks, which can manipulate these models to generate harmful or unintended content. Investigating these attacks is crucial for uncovering model…