{"total":67,"rows":[{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2409.10102","title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","created":"2024-09-16","cited_by_count":83,"area":"rag"},{"id":"2504.03957","title":"Practical Poisoning Attacks against Retrieval-Augmented Generation","created":"2025-04-04","cited_by_count":36,"area":"rag"},{"id":"2410.15236","title":"Jailbreaking and Mitigation of Vulnerabilities in Large Language Models","created":"2024-10-20","cited_by_count":34,"area":"safety"},{"id":"2410.08811","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","created":"2024-10-11","cited_by_count":33,"area":"safety"},{"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,"area":"rag"},{"id":"2601.17548","title":"Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems","created":"2026-01-24","cited_by_count":31,"area":"agents"},{"id":"2409.08045","title":"Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking","created":"2024-09-12","cited_by_count":30,"area":"safety"},{"id":"2604.06811","title":"SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems","created":"2026-04-08","cited_by_count":25,"area":"agents"},{"id":"2410.15267","title":"When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?","created":"2024-10-20","cited_by_count":24,"area":"rag"},{"id":"2501.14050","title":"GraphRAG under Fire","created":"2025-01-23","cited_by_count":24,"area":"rag"},{"id":"2408.04870","title":"ConfusedPilot: Confused Deputy Risks in RAG-based LLMs","created":"2024-08-09","cited_by_count":22,"area":"rag"},{"id":"2505.18543","title":"Benchmarking Poisoning Attacks against Retrieval-Augmented Generation","created":"2025-05-24","cited_by_count":18,"area":"rag"},{"id":"2502.04951","title":"Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search","created":"2025-02-07","cited_by_count":16,"area":null},{"id":"2506.06151","title":"Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems","created":"2025-06-06","cited_by_count":16,"area":"rag"},{"id":"2601.04566","title":"BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents","created":"2026-01-08","cited_by_count":16,"area":"agents"},{"id":"2409.19993","title":"Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges","created":"2024-09-30","cited_by_count":15,"area":"safety"},{"id":"2506.04202","title":"TracLLM: A Generic Framework for Attributing Long Context LLMs","created":"2025-06-04","cited_by_count":13,"area":null},{"id":"2510.09710","title":"SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG","created":"2025-10-10","cited_by_count":13,"area":"rag"},{"id":"2408.09878","title":"Transferring Backdoors between Large Language Models by Knowledge Distillation","created":"2024-08-19","cited_by_count":12,"area":"safety"},{"id":"2509.13772","title":"Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation","created":"2025-09-17","cited_by_count":12,"area":"rag"},{"id":"2512.23343","title":"AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents","created":"2025-12-29","cited_by_count":12,"area":"agents"},{"id":"2411.11407","title":"The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models","created":"2024-11-18","cited_by_count":10,"area":"safety"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2511.01268","title":"Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems","created":"2025-11-03","cited_by_count":9,"area":"rag"},{"id":"2407.20181","title":"Blockchain for Large Language Model Security and Safety: A Holistic Survey","created":"2024-07-26","cited_by_count":8,"area":"safety"},{"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,"area":"rag"},{"id":"2506.11415","title":"Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs","created":"2025-06-13","cited_by_count":8,"area":"rag"},{"id":"2508.03793","title":"AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption","created":"2025-08-05","cited_by_count":7,"area":"rag"},{"id":"2510.18333","title":"Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption","created":"2025-10-21","cited_by_count":7,"area":"safety"},{"id":"2601.03979","title":"SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems","created":"2026-01-07","cited_by_count":7,"area":"rag"},{"id":"2503.06950","title":"CtrlRAG: Black-box Document Poisoning Attacks for Retrieval-Augmented Generation of Large Language Models","created":"2025-03-10","cited_by_count":5,"area":"rag"},{"id":"2502.10440","title":"Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning","created":"2025-02-10","cited_by_count":4,"area":"lr"},{"id":"2507.06850","title":"The Dark Side of LLMs: Agent-based Attack Vectors for System-level Compromise","created":"2025-07-09","cited_by_count":4,"area":"agents"},{"id":"2510.12119","title":"ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation","created":"2025-10-14","cited_by_count":4,"area":"safety"},{"id":"2606.01166","title":"BraveGuard: From Open-World Threats to Safer Computer-Use Agents","created":"2026-05-31","cited_by_count":4,"area":"agents"},{"id":"2412.03824","title":"Towards Data Governance of Frontier AI Models","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2504.21680","title":"Hoist with His Own Petard: Inducing Guardrails to Facilitate Denial-of-Service Attacks on Retrieval-Augmented Generation of LLMs","created":"2025-04-30","cited_by_count":3,"area":"rag"},{"id":"2508.18652","title":"UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation","created":"2025-08-26","cited_by_count":3,"area":"rag"},{"id":"2510.05310","title":"RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts","created":"2025-10-06","cited_by_count":3,"area":"safety"},{"id":"2601.20615","title":"DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning","created":"2026-01-28","cited_by_count":3,"area":"rag"},{"id":"2605.03482","title":"MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents","created":"2026-05-05","cited_by_count":3,"area":"rag"},{"id":"2508.20083","title":"DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version)","created":"2025-08-27","cited_by_count":2,"area":"rag"},{"id":"2603.00516","title":"ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data","created":"2026-02-28","cited_by_count":2,"area":"safety"},{"id":"2605.27157","title":"Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs","created":"2026-05-26","cited_by_count":2,"area":"rag"},{"id":"2506.10030","title":"Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment","created":"2025-06-10","cited_by_count":1,"area":"rag"},{"id":"2509.10682","title":"LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2510.00586","title":"Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors","created":"2025-10-01","cited_by_count":1,"area":"rag"},{"id":"2603.12089","title":"EmbTracker: Traceable Black-box Watermarking for Federated Language Models","created":"2026-03-12","cited_by_count":1,"area":"safety"},{"id":"2605.01782","title":"Needle-in-RAG: Prompt-Conditioned Character-Level Traceback of Poisoned Spans in Retrieved Evidence","created":"2026-05-03","cited_by_count":1,"area":"rag"},{"id":"2606.01212","title":"DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation","created":"2026-05-31","cited_by_count":1,"area":"rag"},{"id":"2606.18310","title":"Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems","created":"2026-06-16","cited_by_count":1,"area":"rag"},{"id":"2508.01084","title":"Provably Secure Retrieval-Augmented Generation","created":"2025-08-01","cited_by_count":0,"area":"rag"},{"id":"2508.15839","title":"CIA+TA Risk Assessment for AI Reasoning Vulnerabilities","created":"2025-08-19","cited_by_count":0,"area":"lr"},{"id":"2508.15934","title":"Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification","created":"2025-08-21","cited_by_count":0,"area":"safety"},{"id":"2604.23483","title":"Agentic Adversarial Rewriting Exposes Architectural Vulnerabilities in Black-Box NLP Pipelines","created":"2026-04-26","cited_by_count":0,"area":"agents"},{"id":"2604.24700","title":"Green Shielding: A User-Centric Approach Towards Trustworthy AI","created":"2026-04-27","cited_by_count":0,"area":"safety"},{"id":"2604.28157","title":"FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption","created":"2026-04-30","cited_by_count":0,"area":"rag"},{"id":"2606.24402","title":"Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents","created":"2026-06-23","cited_by_count":0,"area":"rag"},{"id":"2606.26793","title":"MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG","created":"2026-06-25","cited_by_count":0,"area":"rag"},{"id":"2607.10402","title":"Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.17535","title":"Salience Induction against Multi-Hop RAG Agents: Threat and Defense","created":"2026-07-20","cited_by_count":0,"area":"rag"},{"id":"2607.24893","title":"Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study","created":"2026-07-27","cited_by_count":0,"area":"agents"},{"id":"2609.16694","title":"Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural Perspectives","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.22246","title":"The Corroboration Illusion: When More News Makes LLM Forecasts Less True","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.25469","title":"RAG-NAROK: Retrieval-Aware Knowledge Corpus Poisoning in RAG with Source-specific Refutation","created":"2026-09-21","cited_by_count":0,"area":"rag"},{"id":"2609.37468","title":"Backdoor in the Loop: Compromising Agentic Search via Malicious Retrievers","created":"2026-09-26","cited_by_count":0,"area":"rag"}],"next_cursor":null}