What Standard Evaluations Hide About Detectors of Hijacked LLM Agents: Rare Attacks, Unseen Tools and Benchmark Transfer
cs.CR, cs.LG
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/Mahmoud-Abbasi-svg/agent-trace-detector-eval
Terminology
Sources
- TraceAegis: Securing LLM-Based Agents via Hierarchical and Behavioral Anomaly Detection
- Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents
- Agent-Sentry: Bounding LLM Agents via Execution Provenance
- DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents
- Trajectory Guard -- A Lightweight, Sequence-Aware Model for Real-Time Anomaly Detection in Agentic AI
- Content-Aware Attack Detection in LLM Agent Tool-Call Traffic: An Empirical Study of Features, Architectures, and Evaluation Protocols
- Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modeling
- TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agents
- SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems
- LlamaFirewall: An open source guardrail system for building secure AI agents
- When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift
- AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories
- TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories
- ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
- AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
- Specification-based Security Evaluation of Real-World Agents Tool-Calling under Long-Horizon Context Tasks
- The Llama 3 Herd of Models
- Adam: A Method for Stochastic Optimization
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data