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

Creating secure and resilient applications with large language models (LLM) requires anticipating, adjusting to, and countering unforeseen threats. Red-teaming has emerged as a critical technique for identifying vulnerabilities in…

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to…

As large language models (LLMs) grow in power and influence, ensuring their safety and preventing harmful output becomes critical. Automated red teaming serves as a tool to detect security vulnerabilities in LLMs without manual labor.…

Ensuring the safety of large language models (LLMs) is paramount, yet identifying potential vulnerabilities is challenging. While manual red teaming is effective, it is time-consuming, costly and lacks scalability. Automated red teaming…

As large language models (LLMs) become increasingly prevalent across many real-world applications, understanding and enhancing their robustness to adversarial attacks is of paramount importance. Existing methods for identifying adversarial…

Ensuring safety of large language models (LLMs) is important. Red teaming--a systematic approach to identifying adversarial prompts that elicit harmful responses from target LLMs--has emerged as a crucial safety evaluation method. Within…

Personalized diffusion models (PDMs) have become prominent for adapting pre-trained text-to-image models to generate images of specific subjects using minimal training data. However, PDMs are susceptible to minor adversarial perturbations,…

As LLMs gain persuasive capabilities through extended dialogues, they create new opportunities for studying adversarial conversational behavior in extended interaction settings that traditional single-turn safety evaluations fail to…

Conventional language model (LM) safety alignment relies on a reactive, disjoint procedure: attackers exploit a static model, followed by defensive fine-tuning to patch exposed vulnerabilities. This sequential approach creates a mismatch --…

As large language models (LLMs) are increasingly deployed as black-box components in real-world applications, red teaming has become essential for identifying potential risks. It tests LLMs with adversarial prompts to uncover…

Safety alignment is critical in pre-training large language models (LLMs) to generate responses aligned with human values and refuse harmful queries. Unlike LLM, the current safety alignment of VLMs is often achieved with post-hoc safety…

Language Model Agents (LMAs) are emerging as a powerful primitive for augmenting red-team operations. They can support attack planning, adversary emulation, and the orchestration of multi-step activity such as lateral movement, a core…

As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and…

Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks remains insufficiently evaluated, potentially…

Deep Neural Networks (DNNs) have recently achieved great success in many tasks, which encourages DNNs to be widely used as a machine learning service in model sharing scenarios. However, attackers can easily generate adversarial examples…

Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts…

Large Language Models (LLMs) are set to reshape cybersecurity by augmenting red and blue team operations. Red teams can exploit LLMs to plan attacks, craft phishing content, simulate adversaries, and generate exploit code. Conversely, blue…

The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions. A key challenge is distinguishing therapeutic empathy from maladaptive validation, where supportive…

Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial ``jailbreak'' attacks designed to bypass safety guardrails. Current safety alignment methods depend heavily on static external red…