相关论文: Purple-teaming LLMs with Adversarial Defender Trai…

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…

We address the challenge of generating diverse attack prompts for large language models (LLMs) that elicit harmful behaviors (e.g., insults, sexual content) and are used for safety fine-tuning. Rather than relying on manual prompt…

As large language models (LLMs) continue to advance in capability and influence, ensuring their security and preventing harmful outputs has become crucial. A promising approach to address these concerns involves training models to…

As Large Language Models (LLMs) play an increasingly pivotal role in natural language processing applications, their safety concerns become critical areas of NLP research. This paper presents Safety and Over-Defensiveness Evaluation (SODE)…

In this work, we consider model robustness of deep neural networks against adversarial attacks from a global manifold perspective. Leveraging both the local and global latent information, we propose a novel adversarial training method…

Large language models remain vulnerable to adversarial prompts that elicit harmful outputs. Existing safety paradigms typically couple red-teaming and post-training in a closed, policy-centric loop, causing attack discovery to suffer from…

Large Language Models (LLMs) for code generation (i.e., Code LLMs) have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studies have shown that these models are prone to generating…

The safety of Large Language Models (LLMs) is crucial for the development of trustworthy AI applications. Existing red teaming methods often rely on seed instructions, which limits the semantic diversity of the synthesized adversarial…

Recent studies have discovered that large language models (LLM) may be ``fooled'' to output private information, including training data, system prompts, and personally identifiable information, under carefully crafted adversarial prompts.…

As Large Language Models quickly become ubiquitous, it becomes critical to understand their security vulnerabilities. Recent work shows that text optimizers can produce jailbreaking prompts that bypass moderation and alignment. Drawing from…

Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs.…

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Efforts to ensure the safety of large language models (LLMs) include safety fine-tuning, evaluation, and red teaming. However, despite the widespread use of the Retrieval-Augmented Generation (RAG) framework, AI safety work focuses on…

Deep neural networks have demonstrated cutting edge performance on various tasks including classification. However, it is well known that adversarially designed imperceptible perturbation of the input can mislead advanced classifiers. In…

As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversarial attacks. A key prerequisite to developing these…

Adversarial attacks pose a significant threat to the reliability of pre-trained language models (PLMs) such as GPT, BERT, RoBERTa, and T5. This paper presents Adversarial Robustness through Dynamic Ensemble Learning (ARDEL), a novel scheme…

AI-enabled Security Orchestration, Automation, and Response (SOAR) systems increasingly employ autonomous agents for cyber defense, yet their resilience to adaptive adversaries is underexplored. We introduce an autonomous red teaming…

The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to address jailbreak…

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…

Current evaluations of defenses against prompt attacks in large language model (LLM) applications often overlook two critical factors: the dynamic nature of adversarial behavior and the usability penalties imposed on legitimate users by…