Related papers: FlowSteer: Prompt-Only Workflow Steering Exposes P…

Compared to traditional models, agentic AI represents a highly valuable target for potential attackers as they possess privileged access to data sources and API tools, which are traditionally not incorporated into classical agents. Unlike a…

Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production deployments. We present Prompt Fencing, a novel architectural approach that applies cryptographic…

Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms. A central challenge is detecting scheming, where agents covertly pursue misaligned goals. One approach to mitigating such…

Large Language Model-based Multi-Agent Systems (LLM-MAS) have revolutionized complex problem-solving capability by enabling sophisticated agent collaboration through message-based communications. While the communication framework is crucial…

With the wide application of multimodal foundation models in intelligent agent systems, scenarios such as mobile device control, intelligent assistant interaction, and multimodal task execution are gradually relying on such large…

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal…

Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning…

Despite the growing capabilities of autonomous agents powered by large language models (LLMs), their adoption in high-stakes domains remains limited. A key barrier is security: the inherently nondeterministic behavior of LLM agents defies…

LLM-based multi-agent systems (MAS) demonstrate increasing integration into next-generation applications, but their safety in backdoor attacks remains largely underexplored. However, existing research has focused exclusively on single-agent…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Large language models (LLMs) have empowered nodes within multi-agent networks with intelligence, showing growing applications in both academia and industry. However, how to prevent these networks from generating malicious information…

Multi-agent orchestration -- in which a hidden coordinator manages specialized worker agents -- is becoming the default architecture for enterprise AI deployment, yet the safety implications of orchestrator invisibility have never been…

When large language model (LLM) agents are increasingly deployed to automate tasks and interact with untrusted external data, prompt injection emerges as a significant security threat. By injecting malicious instructions into the data that…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by…

LLM-powered coding agents increasingly make software supply chain decisions. They generate imports, recommend packages, and write installation commands. Prior work showed that these systems can hallucinate non-existent package names, which…

With the proliferation of LLM-driven multi-agent systems (MAS), the security of Web links has become a critical concern. Once MAS is induced to trust a malicious link, attackers can use it as a springboard to expand the attack surface. In…

Large language models (LLMs) are shown to be vulnerable to jailbreaking attacks where adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detecting and filtering…

Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational…

Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example,…

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…