相关论文: Prompt Injection Mitigation with Agentic AI, Neste…

As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on vulnerabilities in single-agent LLMs. These include prompt…

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt…

In this study, a modular, data-free pipeline for multi-label intention recognition is proposed for agentic AI applications in transportation. Unlike traditional intent recognition systems that depend on large, annotated corpora and often…

This paper proposes a novel architectural framework aimed at enhancing security and reliability in multi-agent systems (MAS). A central component of this framework is a network of Sentinel Agents, functioning as a distributed security layer…

Vision-language models (VLMs) have revolutionized multimodal AI applications but introduce novel security vulnerabilities that remain largely unexplored. We present the first comprehensive study of steganographic prompt injection attacks…

Modern language models have enabled the development of agentic systems that achieve strong performance on reasoning-intensive tasks. Unfortunately, this has come with a security cost; these systems are vulnerable to prompt injection, a…

The evolution of Large Language Models (LLMs) has resulted in a paradigm shift towards autonomous agents, necessitating robust security against Prompt Injection (PI) vulnerabilities where untrusted inputs hijack agent behaviors. This SoK…

Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive and reason over real-world scenes. Within this context, environmental signals such as traffic…

Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks.…

As large language models increasingly deployed into agentic systems, existing methods face critical gaps in observing, assessing, and mitigating deployment-specific risks. We present a comprehensive, observability-driven workflow: we…

Prompt injection attacks pose a critical threat to large language models (LLMs), enabling goal hijacking and data leakage. Prompt guard models, though effective in defense, suffer from over-defense -- falsely flagging benign inputs as…

Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies. We present an evaluation methodology for prompt-injection defenses in this setting,…

Computer-Use Agents (CUAs) with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access user data, and execute arbitrary commands. While prior work…

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…

As the industry increasingly adopts agentic AI systems, understanding their unique vulnerabilities becomes critical. Prior research suggests that security flaws at the model level do not fully capture the risks present in agentic…

The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security…

The rapid advancement and widespread adoption of generative artificial intelligence (GenAI) and large language models (LLMs) has been accompanied by the emergence of new security vulnerabilities and challenges, such as jailbreaking and…

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…

Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection (IPI), a black-box attack in which adversarial instructions…