发现信息

  • 作者:Debeshee Das, Julien Piet, Darya Kaviani, Luca Beurer-Kellner, Florian Tramèr, David Wagner
  • 年份:2026
  • 发表源:ACM Workshop on Artificial Intelligence and Security (AISec)
  • OpenAlex ID:https://openalex.org/W7160244616
  • DOI:https://doi.org/10.1145/3847352.3848090
  • arXiv:待核验
  • 检索主题:memory-evaluation
  • OpenAlex 引用数快照:13(2026-11-12)

摘要线索

Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. The Trojan Hippo attack is a class of persistent memory attacks that operates under a more realistic threat model than prior memory poisoning work. The attacker plants a dormant payload into an agent’s long-term memory via a single untrusted tool call (e.g., a crafted email), which activates only when the user later discusses sensitive topics such as finance, health, or identity, and exfiltrates high-value personal data to the attacker. While anecdotal demonstrations of such attacks have appeared against deployed systems, no prior work systematically evaluates them across heterogeneous memory architectures and defenses. We introduce Trojan Hippo Bench, a dynamic evaluation framework for persistent memory attacks and memory-layer defenses, comprising two components: (1) an OpenEvolve-based [ 54 ] adaptive red-teaming benchmark that stress-tests defenses and memory backends against continuously refined attacks, and (2) a capability-aware security–utility analysis for persistent memory systems, enabling principled reasoning about defense deployment across different usage profiles. Instantiated on an email assistant across four memory backends (explicit tool memory, agentic memory, RAG, and sliding-window context), the undefended Trojan Hippo attack achieves up to 85–100% attack success rate (ASR) against current frontier models from OpenAI and Google, with planted memories successfully activating even after 100 benign sessions. We evaluate four memory-system defenses inspired by basic security principles; they reduce attack success to as low as 0–5%, but at utility costs that vary widely with the task mix. Effective real-world deployment thus remains an open challenge that Trojan Hippo Bench is built to study; we release it to support reuse and extension.

核验与筛选

  • 当前状态:待筛选、去重和一手来源核验。
  • OpenAlex 元数据和引用数只用于发现,不作为正式引文或质量判断。
  • 记录正式版本、venue、方法细节、实验协议和局限后,才迁入稳定论文卡片。