arXiv AI
The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems
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
Pretraining Data Can Be Poisoned through Computational Propaganda
arXiv:2607. 15267v1 Announce Type: new Abstract: Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate.
arXiv Computation and Language
Sep 10
An Efficient and Effective Agentic Group Shilling Attack on Recommender Systems
arXiv:2609.09551v1 Announce Type: cross Abstract: Recommender systems have become core infrastructure for modern online platforms, personalizing content at scale and strongly influencing what users s...
arXiv Machine Learning
Jul 22
Beyond Content: Behavioral Policies Reveal Actors in Information Operations
arXiv:2602. 02838v2 Announce Type: replace-cross Abstract: The detection of online influence operations -- coordinated campaigns by malicious actors to spread narratives -- has traditionally depended on content analysis or network features.
arXiv AI
Aug 25
MEMORY Wins All: Indirect Bias Injection Attacks via Social Media Feeds
arXiv:2608.22061v1 Announce Type: new Abstract: Personal AI agents routinely consume external content while performing tasks such as web browsing, email processing, and SNS feed summarization, and th...
arXiv AI
Jun 2
Agent Guide: A Simple Agent Behavioral Watermarking Framework
arXiv:2504. 05871v3 Announce Type: replace Abstract: The increasing deployment of intelligent agents in digital ecosystems, such as social media platforms, has raised significant concerns about traceability and accountability, particularly in cybersecurity and digital content protection.