{"list":"closest","total":70,"rows":[{"id":"2603.25164","title":"PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems","created":"2026-03-26","cited_by_count":1},{"id":"2602.09319","title":"Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation","created":"2026-02-10","cited_by_count":2},{"id":"2602.08668","title":"Retrieval Pivot Attacks in Hybrid RAG: Measuring and Mitigating Amplified Leakage from Vector Seeds to Graph Expansion","created":"2026-02-09","cited_by_count":1},{"id":"2602.04711","title":"Addressing Corpus Knowledge Poisoning Attacks on RAG Using Sparse Attention","created":"2026-02-04","cited_by_count":3},{"id":"2601.17644","title":"Do Multimodal RAG Systems Leak Data? A Comprehensive Evaluation of Membership Inference and Image Caption Retrieval Attacks","created":"2026-01-25","cited_by_count":3},{"id":"2601.15678","title":"Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems","created":"2026-01-22","cited_by_count":3},{"id":"2601.11199","title":"SD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented Generation","created":"2026-01-16","cited_by_count":4},{"id":"2601.10923","title":"Hidden-in-Plain-Text: A Benchmark for Social-Web Indirect Prompt Injection in RAG","created":"2026-01-16","cited_by_count":5},{"id":"2601.03979","title":"SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems","created":"2026-01-07","cited_by_count":7},{"id":"2601.00274","title":"Making Theft Useless: Adulteration-Based Protection of Proprietary Knowledge Graphs in GraphRAG Systems","created":"2026-01-01","cited_by_count":2},{"id":"2512.16962","title":"MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval","created":"2025-12-18","cited_by_count":72},{"id":"2512.08289","title":"MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks","created":"2025-12-09","cited_by_count":4},{"id":"2512.03100","title":"Ensemble Privacy Defense for Knowledge-Intensive LLMs against Membership Inference Attacks","created":"2025-12-01","cited_by_count":1},{"id":"2511.19257","title":"Medusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented Generation","created":"2025-11-24","cited_by_count":2},{"id":"2511.01268","title":"Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems","created":"2025-11-03","cited_by_count":9},{"id":"2510.25025","title":"Secure Retrieval-Augmented Generation against Poisoning Attacks","created":"2025-10-28","cited_by_count":19},{"id":"2510.11195","title":"RAG-Pull: Turning Retrieval into a Code-Injection Channel via Invisible Unicode Perturbations","created":"2025-10-13","cited_by_count":4},{"id":"2510.06719","title":"Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)","created":"2025-10-08","cited_by_count":6},{"id":"2509.23519","title":"ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search","created":"2025-09-27","cited_by_count":18},{"id":"2509.22486","title":"Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks","created":"2025-09-26","cited_by_count":8},{"id":"2509.20324","title":"RAG Security and Privacy: Formalizing the Threat Model and Attack Surface","created":"2025-09-24","cited_by_count":8},{"id":"2509.15159","title":"AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt","created":"2025-09-18","cited_by_count":5},{"id":"2509.07941","title":"ImportSnare: Directed \"Code Manual\" Hijacking in Retrieval-Augmented Code Generation","created":"2025-09-09","cited_by_count":5},{"id":"2508.09105","title":"SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling","created":"2025-08-12","cited_by_count":3},{"id":"2508.03110","title":"Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation","created":"2025-08-05","cited_by_count":5},{"id":"2507.18202","title":"Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection","created":"2025-07-24","cited_by_count":5},{"id":"2507.05093","title":"The Hidden Threat in Plain Text: Attacking RAG Data Loaders","created":"2025-07-07","cited_by_count":8},{"id":"2507.02974","title":"InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy","created":"2025-06-30","cited_by_count":10},{"id":"2506.06151","title":"Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems","created":"2025-06-06","cited_by_count":16},{"id":"2506.00281","title":"Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems","created":"2025-05-30","cited_by_count":4},{"id":"2505.22061","title":"Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home?","created":"2025-05-28","cited_by_count":9},{"id":"2505.18583","title":"The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems","created":"2025-05-24","cited_by_count":10},{"id":"2505.18543","title":"Benchmarking Poisoning Attacks against Retrieval-Augmented Generation","created":"2025-05-24","cited_by_count":18},{"id":"2505.15420","title":"Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries","created":"2025-05-21","cited_by_count":19},{"id":"2505.13957","title":"Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation","created":"2025-05-20","cited_by_count":5},{"id":"2505.11548","title":"One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems","created":"2025-05-15","cited_by_count":28},{"id":"2505.08728","title":"Securing RAG: A Risk Assessment and Mitigation Framework","created":"2025-05-13","cited_by_count":3},{"id":"2505.07546","title":"GRADA: Graph-based Reranking against Adversarial Documents Attack","created":"2025-05-12","cited_by_count":10},{"id":"2505.06311","title":"Defending against Indirect Prompt Injection by Instruction Detection","created":"2025-05-08","cited_by_count":32},{"id":"2504.07717","title":"PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization","created":"2025-04-10","cited_by_count":32},{"id":"2504.02132","title":"One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image","created":"2025-04-02","cited_by_count":8},{"id":"2503.21315","title":"Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack","created":"2025-03-27","cited_by_count":10},{"id":"2503.15548","title":"Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval","created":"2025-03-17","cited_by_count":10},{"id":"2503.06254","title":"Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation","created":"2025-03-08","cited_by_count":12},{"id":"2502.20995","title":"The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems","created":"2025-02-28","cited_by_count":14},{"id":"2502.03233","title":"Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation","created":"2025-02-05","cited_by_count":9},{"id":"2502.01386","title":"Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models","created":"2025-02-03","cited_by_count":33},{"id":"2502.00306","title":"Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation","created":"2025-02-01","cited_by_count":26},{"id":"2501.02968","title":"FlippedRAG: Black-Box Opinion Manipulation Adversarial Attacks to Retrieval-Augmented Generation Models","created":"2025-01-06","cited_by_count":25},{"id":"2501.00879","title":"TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation","created":"2025-01-01","cited_by_count":40},{"id":"2412.20953","title":"GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search","created":"2024-12-30","cited_by_count":20},{"id":"2412.19291","title":"RAG with Differential Privacy","created":"2024-12-26","cited_by_count":18},{"id":"2412.13163","title":"C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System","created":"2024-12-17","cited_by_count":19},{"id":"2412.12775","title":"RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service","created":"2024-12-17","cited_by_count":17},{"id":"2412.04697","title":"Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy","created":"2024-12-06","cited_by_count":39},{"id":"2411.18948","title":"RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis","created":"2024-11-28","cited_by_count":33},{"id":"2411.01705","title":"Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors","created":"2024-11-03","cited_by_count":23},{"id":"2408.05025","title":"Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworks","created":"2024-08-09","cited_by_count":17},{"id":"2408.04870","title":"ConfusedPilot: Confused Deputy Risks in RAG-based LLMs","created":"2024-08-09","cited_by_count":22},{"id":"2406.19417","title":"\"Glue pizza and eat rocks\" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models","created":"2024-06-26","cited_by_count":60},{"id":"2406.14773","title":"Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data","created":"2024-06-20","cited_by_count":52},{"id":"2406.05870","title":"Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents","created":"2024-06-09","cited_by_count":102},{"id":"2406.05087","title":"Corpus Poisoning via Approximate Greedy Gradient Descent","created":"2024-06-07","cited_by_count":21},{"id":"2405.20485","title":"Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation","created":"2024-05-30","cited_by_count":49},{"id":"2405.15556","title":"Certifiably Robust RAG against Retrieval Corruption","created":"2024-05-24","cited_by_count":151},{"id":"2404.17196","title":"Human-Imperceptible Retrieval Poisoning Attacks in LLM-Powered Applications","created":"2024-04-26","cited_by_count":33},{"id":"2404.13948","title":"Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations","created":"2024-04-22","cited_by_count":65},{"id":"2402.17840","title":"Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems","created":"2024-02-27","cited_by_count":76},{"id":"2402.16893","title":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)","created":"2024-02-23","cited_by_count":159},{"id":"2402.07867","title":"PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models","created":"2024-02-12","cited_by_count":267}],"next_cursor":null}