MEMORY Wins All: Indirect Bias Injection Attacks via Social Media Content
cs.AI, cs.CY
Submitted: 2026-08-22
Updated: 2026-11-03
Code: https://github.com/unitaryai/detoxify
Terminology
Sources
- Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification
- From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
- SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration
- SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
- Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
- "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
- Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems
- MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
- Behavioral Integrity Verification for AI Agent Skills
- ReAct: Synergizing Reasoning and Acting in Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents