The paper systematically evaluates various defense mechanisms against persistent memory attacks on LLM agents, finding that only tool-gating at the memory layer (Memory Sandbox) effectively mitigates…

The paper proposes MemPoison, a novel memory poisoning attack that injects triggerable backdoors into LLM agents' long-term memory through dialogue interactions, achieving high success rates by bypass…

The paper introduces MemPoison, a novel memory poisoning attack that successfully injects triggerable backdoors into LLM agents' long-term memory through conversational interactions, achieving high at…

MemMorph introduces a novel memory poisoning attack that biases LLM agent tool selection by injecting crafted records into the agent's long-term memory, achieving high success rates even against moder…

This paper systematically studies memory poisoning attacks in LLM agents, identifying multiple vulnerabilities and proposing a new benchmark to assess the risk.

The paper introduces MemSecBench, a benchmark for evaluating the lifecycle security of agent memory systems against malicious semantics, and reports results across various configurations.

The paper introduces eTAMP, a novel attack that poisons LLM web agents' memory using only environmental observations, demonstrating cross-site and cross-session compromise without direct memory access…

The paper proposes the Layered Attack Surface Model (LASM), a structural taxonomy that maps security threats and defenses across the complex, multi-layered architecture of AI agents, revealing signifi…

The paper introduces MAGE, a novel defensive framework that uses a dedicated 'shadow memory' to proactively detect and mitigate long-horizon threats against LLM agents during complex, multi-step inter…

MemLineage introduces a novel, cryptographically-backed defense mechanism that enforces a chain-of-custody for LLM agent memory, preventing untrusted or poisoned state from justifying sensitive action…

The paper introduces Honeyval, a comprehensive evaluation framework, to rigorously test LLM-powered HTTP honeypots, demonstrating that these honeypots provide substantially longer and harder-to-detect…

The paper introduces Honeyval, a comprehensive evaluation framework, to rigorously test LLM-powered HTTP honeypots, demonstrating that these systems provide substantially longer and harder-to-detect i…

This paper investigates the OS resilience to a new class of attacks called self-state attacks, where an agent's state is compromised via legitimate OS system call invocation. It characterizes the atta…

This survey establishes persistent, writable memory as an independent security problem for LLM agents, proposing a comprehensive framework for 'mnemonic sovereignty' to govern the entire memory lifecy…

This paper analyzes memory poisoning attacks targeting multi-agent systems (MAS) powered by LLMs, proposing mitigation strategies across various memory types, especially focusing on secure design prin…

This paper introduces ClawTrojan, a benchmark for multi-step trojan attacks against LLM agents, and proposes DASGuard, a dynamic defense mechanism that traces and sanitizes untrusted control content i…

The paper introduces ClawTrojan, a benchmark for multi-step trojan attacks against LLM agents, and proposes DASGuard, a defense mechanism that detects and sanitizes backdoor content planted across mul…

The paper introduces and evaluates 'sleeper memory poisoning,' a delayed adversarial attack that corrupts an LLM agent's persistent memory by manipulating external context, demonstrating that these po…

Red-MIRROR is a novel multi-agent LLM system that automates complex web penetration testing by integrating a memory-reflection backbone, achieving superior performance on industry benchmarks.

The paper introduces a multi-dimensional evasion framework and a new benchmark (A3S-Bench) to test autonomous agents, demonstrating that stateful, multi-turn attacks significantly increase system risk…