Related papers: Cross-Session Threats in AI Agents: Benchmark, Eva…

Large Language Models (LLMs) exhibit impressive capabilities, but remain susceptible to a growing spectrum of safety risks, including jailbreaks, toxic content, hallucinations, and bias. Existing defenses often address only a single threat…

Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in causal language models. Our approach relies on two key…

Machine learning is a field of artificial intelligence (AI) that is becoming essential for several critical systems, making it a good target for threat actors. Threat actors exploit different Tactics, Techniques, and Procedures (TTPs)…

Large language models (LLMs) are increasingly used as analyst assistants in security operations centers (SOCs), where they ingest log and alert data to produce triage labels, incident summaries, or remediation advice. We study a structural…

Collaborative multi-agent reinforcement learning has rapidly evolved, offering state-of-the-art algorithms for real-world applications, including sensitive domains. However, a key challenge to its widespread adoption is the lack of a…

Artificial intelligence (AI) systems are being readily and rapidly adopted, increasingly permeating critical domains: from consumer platforms and enterprise software to networked systems with embedded agents. While this has unlocked…

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on…

The evolution of large language models into autonomous agents introduces adversarial failures that exploit legitimate tool privileges, transforming safety evaluation in tool-augmented environments from a subjective NLP task into an…

AI agents aim to solve complex tasks by combining text-based reasoning with external tool calls. Unfortunately, AI agents are vulnerable to prompt injection attacks where data returned by external tools hijacks the agent to execute…

As artificial intelligence (AI) systems are increasingly deployed across critical domains, their security vulnerabilities pose growing risks of high-profile exploits and consequential system failures. Yet systematic approaches to evaluating…

Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…

Existing backdoor attacks on Large Language Model-based agents remain stateless, executing fixed behaviors confined to a single session. We propose a stateful agent backdoor that extends the attack lifecycle across multiple sessions under…

Memory poisoning attacks for Agentic AI and multi-agent systems (MAS) have recently caught attention. It is partially due to the fact that Large Language Models (LLMs) facilitate the construction and deployment of agents. Different memory…

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

Large Language Model (LLM) agents increasingly serve as personal assistants and workplace collaborators, where their utility depends on memory systems that extract, retrieve, and apply information across long-running conversations. However,…

We introduce MemLineage, a defense for LLM agent memory that attaches both cryptographic provenance and LLM-mediated derivation lineage to every entry. Recent and concurrent work shows that untrusted content can be written into persistent…

The Model Context Protocol (MCP) has become a widely adopted interface for LLM agents to invoke external tools, yet learned monitoring of MCP tool-call traffic remains underexplored. In this article, the proposed detector is presented as an…

Cybersecurity has become one of the earliest adopters of agentic AI, as security operations centers increasingly rely on multi-step reasoning, tool-driven analysis, and rapid decision-making under pressure. While individual large language…

Multi-agent Large Language Model (LLM) systems create privacy risks that current benchmarks cannot measure. When agents coordinate on tasks, sensitive data passes through inter-agent messages, shared memory, and tool arguments, all pathways…

Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…