Persistent memory in LLM agents widens privacy leakage over sessions
Instructing the agent not to state or presuppose attributes cut leakage near the no-memory level while keeping most quality gains.
Stories per day · 30 days
5 stories, newest first · one card per story
Stories tagged #persistent-memory
APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants
APM-Bench evaluates persistent memory for streaming video assistants across 104 multi-session trajectories.
Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents
Shared artifacts can carry adversarial prompts across LLM agents, infecting most of them within eight hops.
Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems
16-day multi-agent stress test finds no world fully resilient to prompt injection, misinformation, or memory exposure; adversarial content acted on 46 hours later.
LLMs and Contextual Integrity
Bruce Schneier highlights two papers: the CIMemories benchmark shows frontier LLMs leak memory attributes up to 69%, and an RL method reduces inappropriate disclosures.
4