open-weight-agents-where-attention-matrices-accessible-detecting-injection-asking
mechanismsingle paperpending review

For open-weight agents where attention matrices are accessible, detecting injection by asking which context span actually drove the tool call — aggregating attention over the decision tokens and localizing the guiding span, then checking whether that span's provider has authority for the action — catches unauthorized tool invocations at higher true-positive and lower false-positive rates than static scanners that look for malicious-looking text, because benign-looking injected text is only harmful when it is what the model actually attends to.

Ingested from a paper but not yet reviewed by a human. It is deliberately inert: it does not move any technique’s standing, does not count toward the backtest, and is excluded anywhere a claim would carry weight. Read the source before relying on it.

Capability: Following instructions hidden in data

Observed on

Requires white-box access to attention during inference, plus provenance annotations that map token positions to providers; evaluated on tool-metadata poisoning and indirect prompt.

Sources

  • Measured on MCPTox and InjecAgent across ten agent configurations from six model families, against static scanning (LLM-Guard, LLM Detector), behavior auditing (MCIP), and attribution baselines (MindGuard, TracLLM). Reported average AUROC 0.956 and 0.934 TPR at 0.067 FPR; static scanners were near 0.5-0.67 TPR with FPR above 0.36. Detectors are trained per model-dataset pair in the main table, so headline numbers are not a fully unseen-deployment estimate; transfer results are lower. [truncated]
Status: pending-reviewLast checked: 2026-09-09Evidence activity: not checked yet
Contest this claim

Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.

Related claims

Notes

Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: A study finding that the localized high-attention span does not correspond to the span that changes the tool call under ablation, or that static/content-based scanners match this detection rate at equal false-positive rate on the same benchmarks. Proposed technique, not catalogued: attention-localized behavior-guiding span adjudication.