LENS: The Sum Is Worse Than the Parts for Set-Level Poisoning in Retrieval-Augmented Generation
cs.CR
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation
- FlippedRAG: Black-Box Opinion Manipulation Adversarial Attacks to Retrieval-Augmented Generation Models
- Secure Retrieval-Augmented Generation against Poisoning Attacks
- KidnapRAG: A Black-Box Attack for Hijacking Reasoning in Agentic Retrieval-Augmented Generation Systems
- Defending Against Knowledge Poisoning Attacks During Retrieval-Augmented Generation
- The Llama 3 Herd of Models
- Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems
- Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender Systems
- FORGE: Research-Trajectory Hijacking Attacks on Deep Research Agents
- SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning
- SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
- Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG Systems
- PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems
- BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation
- TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs