Retrieval Observability Bounds on Provenance Detection for Agent Memory Poisoning: Measured Coverage and a Falsified Standalone Detector

arXiv:2606.30566 · cs.CR, cs.LG · Submitted 2026-06-29 · Read on arXiv

cs.CR, cs.LG

Submitted: 2026-06-29

Updated: 2026-09-27

Terminology

• AUC — 49× in this paper · explained in 2 episodes
• RAG — 24× in this paper · explained in 3 episodes
• Random Forest — 13× in this paper
• Trace — 9× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Generalization — 5× in this paper · explained in 13 episodes
• Calibration — 4× in this paper · explained in 7 episodes
• Agent Memory — 3× in this paper · explained in 1 episode
• Agentic System — 3× in this paper · explained in 2 episodes
• Core — 3× in this paper · explained in 2 episodes
• LLM judge — 3× in this paper · explained in 2 episodes
• Provenance — 3× in this paper · explained in 3 episodes
• Agentic Framework — 2× in this paper · explained in 6 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Logistic Regression — 2× in this paper
• Model-Agnostic — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Agent Architectures — 1× in this paper · explained in 1 episode
• Agent Skills — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Archetype — 1× in this paper · explained in 1 episode
• Feature Engineering — 1× in this paper · explained in 3 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Representation Engineering — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Steering — 1× in this paper · explained in 2 episodes

Sources

• Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents
• From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
• PerD: Perturbation Sensitivity-based Neural Trojan Detection Framework on NLP Applications
• MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents
• Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents
• VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills
• TraceAegis: Securing LLM-Based Agents via Hierarchical and Behavioral Anomaly Detection
• MemLineage: Lineage-Guided Enforcement for LLM Agent Memory
• Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
• What If Prompt Injection Never Left? Rethinking Agent Security through Cross-Session Stored Prompt Injection
• Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
• MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning
• Representation Engineering: A Top-Down Approach to AI Transparency

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs