FIELD NOTES TOPIC
attack
3 notes, newest first.
Agent Data Injection Attacks are Realistic Threats to AI Agents
The research paper introduces a new type of attack called Agent Data Injection (ADI), which can manipulate AI agents by injecting malicious data disguised as trusted data. This attack can cause agents to execute…
Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses
Researchers have identified a new type of attack, called Forged Amplifying Rationale Memory Attack (FARMA), that can manipulate a large language model (LLM) agent's reasoning history by inserting forged traces using…
Distributed Attacks in Persistent-State AI Control
Researchers introduce Iterative VibeCoding, a setting for AI control where an autonomous coding agent builds software over a series of pull requests in a persistent codebase while pursuing a covert side task. The study…
