Salience Induction against Multi-Hop RAG Agents: Threat and Defense

arXiv:2607.17535 · cs.CR, cs.CL · Submitted 2026-07-20 · Read on arXiv

Xingfu Zhou, Pengfei Wang, Yuan Zhou, Wei Xie, Xu Zhou

cs.CR, cs.CL

Submitted: 2026-07-20

Comments: 18 pages, 4 figures, 12 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• RAG — 47× in this paper · explained in 3 episodes
• Benchmark — 28× in this paper · explained in 2 episodes
• Verifier — 20× in this paper · explained in 2 episodes
• Trace — 15× in this paper · explained in 2 episodes
• Salience Normalization — 13× in this paper
• Ablation — 12× in this paper · explained in 1 episode
• Verification — 10× in this paper · explained in 2 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Agent Architectures — 8× in this paper · explained in 1 episode
• Robustness — 7× in this paper · explained in 5 episodes
• Consistency — 6× in this paper · explained in 3 episodes
• Decoupling — 5× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 5× in this paper
• Adversarial Attacks — 3× in this paper · explained in 1 episode
• Agentic Retrieval — 3× in this paper · explained in 1 episode
• Empirical Methods in Natural Language Processing — 3× in this paper
• Generalization — 3× in this paper · explained in 13 episodes
• Meeting of the Association for Computational Linguistics — 3× in this paper
• Multi-hop Reasoning — 3× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation (RAG) — 3× in this paper · explained in 16 episodes
• Self-consistency — 3× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Transactions of the Association for Computational Linguistics — 2× in this paper
• Adam — 1× in this paper · explained in 2 episodes
• Adversarial Examples — 1× in this paper · explained in 2 episodes
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Commentary — 1× in this paper · explained in 2 episodes
• Cross-Model Transfer — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• International Conference on Machine Learning — 1× in this paper
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes

Sources

• Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation
• M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
• TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
• Knowledge-Augmented Language Model Verification
• ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
• Certifiably Robust RAG against Retrieval Corruption
• BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
• Chain-of-Thought Hijacking
• Universal and Transferable Adversarial Attacks on Aligned Language Models

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