Research
SIEVE: Selective Integrity Verification and Escalation for Defending LLM Agents against Indirect Prompt Injection
Publication date not yet evaluated · Added arxiv.org
Page published
Coverage timeline
Single-source research — one report is available.
Why it matters
SIEVE offers defenders a lower-overhead selective-verification approach to blocking indirect prompt injection that steers agents into unauthorized state-changing actions like unauthorized payments or data leakage.
SIEVE is a defense method for LLM agents against indirect prompt injection (IPI), verifying tool transitions and argument sources against an Intent Graph and escalating ambiguous actions to semantic adjudication. Evaluated on AgentLure and AgentDojo against MELON, DRIFT, IPIGuard, and ARGUS, it achieves 5.94% ASR with 97.5% clean utility on AgentLure and 0.34% ASR with 87.63% clean utility on AgentDojo, with the lowest token and API-call overhead.