Related papers: WebWeaver: Breaking Topology Confidentiality in LL…

This paper presents a defense framework for enhancing the safety of large language model (LLM) empowered multi-agent systems (MAS) in safety-critical domains such as aerospace. We apply randomized smoothing, a statistical robustness…

In today's digital world, casual user-generated content often contains subtle cues that may inadvertently expose sensitive personal attributes. Such risks underscore the growing importance of effective text anonymization to safeguard…

Despite significant advancements in alignment and content moderation, large language models (LLMs) and text-to-image (T2I) systems remain vulnerable to prompt-based attacks known as jailbreaks. Unlike traditional adversarial examples…

The challenge of WAD (web attack detection) is growing as hackers continuously refine their methods to evade traditional detection. Deep learning models excel in handling complex unknown attacks due to their strong generalization and…

Non-transferable learning (NTL) has been proposed to protect model intellectual property (IP) by creating a "non-transferable barrier" to restrict generalization from authorized to unauthorized domains. Recently, well-designed attack, which…

Large language models (LLMs) have demonstrated exceptional capabilities in text understanding and generation, and they are increasingly being utilized across various domains to enhance productivity. However, due to the high costs of…

Tool-use large language model (LLM) agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory management. While prior research has examined various threats,…

As large language models (LLMs) are increasingly deployed in diverse applications, including chatbot assistants and code generation, aligning their behavior with safety and ethical standards has become paramount. However, jailbreak attacks,…

Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who…

Recent advances in large language models (LLMs) have raised concerns about jailbreaking attacks, i.e., prompts that bypass safety mechanisms. This paper investigates the use of multi-agent LLM systems as a defence against such attacks. We…

Automated intrusion-style workflows require LLM agents to reason over partial observations, tool outputs, and executable artifacts under bounded budgets. A single LLM instance often compresses evidence extraction, planning, execution, and…

The rapid proliferation of online misinformation threatens the stability of digital social systems and poses significant risks to public trust, policy, and safety, necessitating reliable automated fake news detection. Existing methods often…

Large Vision Language Models (LVLMs) demonstrate strong capabilities in multimodal reasoning and many real-world applications, such as visual question answering. However, LVLMs are highly vulnerable to jailbreaking attacks. This paper…

The growing use of large language model (LLM)-based conversational agents to manage sensitive user data raises significant privacy concerns. While these agents excel at understanding and acting on context, this capability can be exploited…

The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed…

Multi-agent systems (MAS) powered by LLMs promise adaptive, reasoning-driven enterprise workflows, yet granting agents autonomous control over tools, memory, and communication introduces attack surfaces absent from deterministic pipelines.…

LLM watermarking has attracted attention as a promising way to detect AI-generated content, with some works suggesting that current schemes may already be fit for deployment. In this work we dispute this claim, identifying watermark…

Large Language Model-based Multi-Agent Systems (LLM-based MAS), where multiple LLM agents collaborate to solve complex tasks, have shown impressive performance in many areas. However, MAS are typically distributed across different devices…

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…