arXiv AI
AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 11
DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents
DriftNet is a dual‑head trajectory Transformer designed to detect and localize prompt injection attacks in large language model agents. It processes logged tool‑call trajectories, classifying each as compromised or not while labeling every step as benign, injection point, hijacked, or failed injection. On the AgentDrift benchmark, DriftNet achieves high accuracy, with an F1 score of 0.983, 98.7% exact injection‑point recovery, and low false‑alarm rates.
arXiv Machine Learning
Jul 30
AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents
arXiv:2607. 26998v1 Announce Type: cross Abstract: Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools.
arXiv AI
Aug 10
Long-Horizon Agent Trajectory Attribution: A Unified Benchmark and Fine-Grained Annotation Framework
arXiv:2608. 06909v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate through long-horizon trajectories involving user instructions, tool use, external observations, and memory.
arXiv AI
Oct 7
Towards a Unified Misuse Monitoring Benchmark
The paper introduces a unified framework for monitoring misuse of large language model agents in multi‑actor settings, focusing on two attack types: decomposition attacks and prompt injection attacks. It proposes tracking the agent’s externalised actions and determining whether the first detection of harm falls within a defined harm window. Using this formalism, the authors build a benchmark of about 6,200 conversation transcripts and evaluate 17 monitor configurations, finding that action‑framed monitors perform well on both threats while content‑framed monitors struggle with injection attacks, and highlighting limitations of traditional position‑blind metrics.
arXiv AI
6d ago
AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
AgentSentry is an inference‑time defense for tool‑augmented large language model agents that mitigates indirect prompt injection (IPI) attacks. It uses temporal causal diagnostics by performing counterfactual re‑executions at tool‑return boundaries to detect mediator‑sensitive proposals, purifies implicated content, and resumes execution from a sanitized state. Evaluations on AgentDojo show zero successful attacks (ASR = 0%) and an average Utility Under Attack of 76.10%, outperforming baselines while maintaining low false‑positive rates.
arXiv AI
Jun 12
Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents
arXiv:2606. 13385v1 Announce Type: cross Abstract: Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences.