arXiv AI
Memetic Trojans: Social Contagions as Carriers of Adversarial Payloads in Agent Networks
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
2d ago
VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents
arXiv:2609.38270v1 Announce Type: cross Abstract: Advancing beyond traditional static scoring models, LLM-powered agentic recommender systems (LLM-ARS) instantiate users and items as autonomous agent...
arXiv AI
Jul 17
AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
arXiv:2603. 15727v3 Announce Type: replace-cross Abstract: Autonomous LLM-based agents increasingly operate as long-running processes forming densely interconnected multi-agent ecosystems, whose security properties remain largely unexplored.
arXiv AI
Aug 12
Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems
arXiv:2608. 10218v1 Announce Type: new Abstract: AI agents are becoming more autonomous and increasingly interconnected, exposing them to new emergent risks arising from agent-to-agent interaction.
arXiv AI
Jun 3
AI Agents Enable Adaptive Computer Worms
arXiv:2606. 03811v1 Announce Type: cross Abstract: A computer worm is malware that spreads on a network by replicating itself from one machine to another.
arXiv Machine Learning
Jul 1
When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
arXiv:2605. 01133v3 Announce Type: replace-cross Abstract: Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks.
arXiv AI
Sep 18
Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems
The paper introduces the Generic Multi-Agent Trading System (GMATS), a framework for studying how large language model (LLM) based trading stacks react to black-box, input-only attacks that inject plausible social‑media content. It defines contagion metrics—belief‑shift scores at analyst and coordinator layers and attack‑clean deltas on backtest metrics—to trace the spread of adversarial signals. Experiments on a safe offline benchmark show that even simple attackers can significantly degrade risk‑return profiles, while certain multi‑agent topologies and coordinator prompts can mitigate these effects.