ClawGuard: Out-of-Band Detection of LLM Agent Workflow Hijacking via EM Side Channel
Leo Linqian Gan (1), Jeffery Wu (1), Longyuan Ge (1), Lanqing Yang (1), Yonghao Song (1), Jingkai Zhang (1), Haojia Jin (1), Weiyi Wang (1), Guangtao Xue (1) ((1) Shanghai Jiao Tong University)

TL;DR
ClawGuard is a passive EM side-channel system that detects LLM agent workflow hijacking by analyzing electromagnetic emissions, offering a forge-resistant security method independent of host OS logs.
Contribution
It introduces a novel out-of-band EM sensing approach for detecting compromised LLM workflows, surpassing traditional host-internal telemetry defenses.
Findings
Achieved 0.9945 AUC in detecting attacks
Detected attacks with 100% true-positive rate
False-positive rate was only 1.16%
Abstract
Autonomous LLM agents face a critical security risk known as workflow hijacking, where attackers subtly alter tool and skill invocations. Existing defenses rely on host-internal telemetry (such as audit logs), which can be forged if the host OS is compromised. To solve this, we introduce ClawGuard, a passive, out-of-band monitor that audits LLM-agent workflows using electromagnetic (EM) emanations. Because distinct agent skills create unique hardware usage patterns (computation, DRAM, network blocking), they emit measurable, macroscopic EM envelopes. External software-defined radios (SDRs) capture these physical signals. Using a drift-aware pipeline with 320-dimensional features, ClawGuard converts RF streams into physical evidence. Evaluated on a 7.82TB RF corpus, ClawGuard achieved an AUC of 0.9945, detecting attacks with a 100% true-positive rate and a 1.16% false-positive rate. This…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
