Trojan Hippo attacks on LLM agent memory achieve 85-100% success rates in data exfiltration across four memory backends even after 100 benign sessions, while evaluated defenses reduce success rates but impose varying utility costs.
Weitang Liu, Xiaoyun Wang, John Owens, and Yixuan Li
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
MEMSAD links anomaly detection gradients to retrieval objectives under encoder regularity to certify detection of continuous memory poisons, achieving perfect TPR/FPR in experiments while exposing a synonym-invariance gap.
Agentic memory improves clean reasoning but worsens performance when spurious patterns are present in stored trajectories; CAMEL calibration reduces this reliance while preserving clean performance.
Policy directives can be lost during context assembly in language model agents, leading to unprompted policy violations that SafeContext can partially prevent.
AgentWard organizes stage-specific security controls with cross-layer coordination to intercept threats across the full lifecycle of autonomous AI agents.
citing papers explorer
-
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
Trojan Hippo attacks on LLM agent memory achieve 85-100% success rates in data exfiltration across four memory backends even after 100 benign sessions, while evaluated defenses reduce success rates but impose varying utility costs.
-
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
-
MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents
MEMSAD links anomaly detection gradients to retrieval objectives under encoder regularity to certify detection of continuous memory poisons, achieving perfect TPR/FPR in experiments while exposing a synonym-invariance gap.
-
The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory
Agentic memory improves clean reasoning but worsens performance when spurious patterns are present in stored trajectories; CAMEL calibration reduces this reliance while preserving clean performance.
-
Ghost in the Context: Measuring Policy-Carriage Failures in Decision-Time Assembly
Policy directives can be lost during context assembly in language model agents, leading to unprompted policy violations that SafeContext can partially prevent.
-
AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents
AgentWard organizes stage-specific security controls with cross-layer coordination to intercept threats across the full lifecycle of autonomous AI agents.