{"total":80,"rows":[{"id":"2407.12784","title":"AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases","created":"2024-07-17","cited_by_count":429,"area":"agents"},{"id":"2402.11208","title":"Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents","created":"2024-02-17","cited_by_count":137,"area":"agents"},{"id":"2510.02373","title":"A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory","created":"2025-09-29","cited_by_count":67,"area":"agents"},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2402.08577","title":"Test-Time Backdoor Attacks on Multimodal Large Language Models","created":"2024-02-13","cited_by_count":40,"area":"mllm"},{"id":"2410.08811","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","created":"2024-10-11","cited_by_count":33,"area":"safety"},{"id":"2411.12768","title":"CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization","created":"2024-11-18","cited_by_count":33,"area":"safety"},{"id":"2504.05605","title":"ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs","created":"2025-04-08","cited_by_count":30,"area":"lr"},{"id":"2406.05948","title":"Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models","created":"2024-06-10","cited_by_count":28,"area":"safety"},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2406.12257","title":"CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models","created":"2024-06-18","cited_by_count":24,"area":"safety"},{"id":"2503.16248","title":"Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents","created":"2025-03-20","cited_by_count":24,"area":"safety"},{"id":"2505.14667","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","created":"2025-05-20","cited_by_count":24,"area":"lr"},{"id":"2604.02623","title":"Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents","created":"2026-04-03","cited_by_count":24,"area":"agents"},{"id":"2503.01781","title":"Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models","created":"2025-03-03","cited_by_count":23,"area":"lr"},{"id":"2402.10196","title":"A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents","created":"2024-02-15","cited_by_count":22,"area":"agents"},{"id":"2403.04780","title":"Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining","created":"2024-03-02","cited_by_count":20,"area":null},{"id":"2501.18617","title":"DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs","created":"2025-01-24","cited_by_count":20,"area":"lr"},{"id":"2502.13141","title":"UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models","created":"2025-02-18","cited_by_count":16,"area":"safety"},{"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":"2505.12567","title":"A Survey of Attacks on Large Language Models","created":"2025-05-18","cited_by_count":15,"area":"agents"},{"id":"2404.19597","title":"TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning","created":"2024-04-30","cited_by_count":14,"area":"safety"},{"id":"2504.17130","title":"Steering the CensorShip: Uncovering Representation Vectors for LLM \"Thought\" Control","created":"2025-04-23","cited_by_count":14,"area":"lr"},{"id":"2407.11282","title":"Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models","created":"2024-07-15","cited_by_count":13,"area":"safety"},{"id":"2408.09878","title":"Transferring Backdoors between Large Language Models by Knowledge Distillation","created":"2024-08-19","cited_by_count":12,"area":"safety"},{"id":"2502.18511","title":"ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models","created":"2025-02-22","cited_by_count":11,"area":"safety"},{"id":"2405.20770","title":"Large Language Model Sentinel: LLM Agent for Adversarial Purification","created":"2024-05-24","cited_by_count":10,"area":"agents"},{"id":"2505.17601","title":"Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs","created":"2025-05-23","cited_by_count":10,"area":"safety"},{"id":"2509.21761","title":"Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models","created":"2025-09-26","cited_by_count":10,"area":"safety"},{"id":"2412.02454","title":"Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining","created":"2024-12-03","cited_by_count":9,"area":"safety"},{"id":"2510.27623","title":"BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning","created":"2025-10-31","cited_by_count":9,"area":"mllm"},{"id":"2410.21791","title":"Enhancing Adversarial Attacks through Chain of Thought","created":"2024-10-29","cited_by_count":8,"area":"lr"},{"id":"2412.11934","title":"Stepwise Reasoning Error Disruption Attack of LLMs","created":"2024-12-16","cited_by_count":8,"area":"lr"},{"id":"2505.23715","title":"Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models","created":"2025-05-29","cited_by_count":8,"area":"lr"},{"id":"2501.18626","title":"The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs","created":"2025-01-27","cited_by_count":7,"area":"safety"},{"id":"2507.18305","title":"BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit","created":"2025-07-24","cited_by_count":7,"area":"lr"},{"id":"2508.03793","title":"AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption","created":"2025-08-05","cited_by_count":7,"area":"rag"},{"id":"2410.19000","title":"Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning","created":"2024-10-18","cited_by_count":6,"area":"lr"},{"id":"2509.24240","title":"Takedown: How It's Done in Modern Coding Agent Exploits","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2410.11283","title":"AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment","created":"2024-10-15","cited_by_count":5,"area":"alignment"},{"id":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2507.23554","title":"DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer","created":"2025-07-31","cited_by_count":5,"area":"agents"},{"id":"2510.07505","title":"PEAR: Planner-Executor Agent Robustness Benchmark","created":"2025-10-08","cited_by_count":5,"area":"agents"},{"id":"2510.15965","title":"One Token Embedding Is Enough to Deadlock Your Large Reasoning Model","created":"2025-10-12","cited_by_count":5,"area":"lr"},{"id":"2505.19405","title":"CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems","created":"2025-05-26","cited_by_count":4,"area":"lr"},{"id":"2507.11112","title":"Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs","created":"2025-07-15","cited_by_count":4,"area":"safety"},{"id":"2406.05660","title":"Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models","created":"2024-06-09","cited_by_count":3,"area":"safety"},{"id":"2602.00380","title":"Clause-Internal or Clause-External? Testing Turkish Reflexive Binding in Adapted versus Chain of Thought Large Language Models","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2602.07652","title":"Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agents","created":"2026-02-07","cited_by_count":3,"area":"agents"},{"id":"2602.11096","title":"Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away","created":"2026-02-11","cited_by_count":3,"area":"lr"},{"id":"2509.24408","title":"FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systems","created":"2025-09-29","cited_by_count":2,"area":"driving"},{"id":"2511.17671","title":"MURMUR: Using cross-user chatter to break collaborative language agents in groups","created":"2025-11-21","cited_by_count":2,"area":"agents"},{"id":"2512.01848","title":"Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability","created":"2025-12-01","cited_by_count":2,"area":"lr"},{"id":"2603.04259","title":"When AI Fails, What Works? A Data-Driven Taxonomy of Real-World AI Risk Mitigation Strategies","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2603.25412","title":"Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models","created":"2026-03-26","cited_by_count":2,"area":"lr"},{"id":"2604.09235","title":"Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor","created":"2026-04-10","cited_by_count":2,"area":"safety"},{"id":"2510.09260","title":"GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis","created":"2025-10-10","cited_by_count":1,"area":"alignment"},{"id":"2511.12861","title":"From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models","created":"2025-11-17","cited_by_count":1,"area":"lr"},{"id":"2604.21700","title":"Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers","created":"2026-04-23","cited_by_count":1,"area":"safety"},{"id":"2606.10742","title":"MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2508.03986","title":"The Emotional Baby Is Truly Deadly: Does your Multimodal Large Reasoning Model Have Emotional Flattery towards Humans?","created":"2025-08-06","cited_by_count":0,"area":"lr"},{"id":"2508.19321","title":"An Investigation on Group Query Hallucination Attacks","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2509.04615","title":"Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs","created":"2025-09-04","cited_by_count":0,"area":"alignment"},{"id":"2509.05318","title":"Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models","created":"2025-08-30","cited_by_count":0,"area":"safety"},{"id":"2603.17174","title":"Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning","created":"2026-03-17","cited_by_count":0,"area":"safety"},{"id":"2604.25247","title":"R-CoT: A Reasoning-Layer Watermark via Redundant Chain-of-Thought in Large Language Models","created":"2026-04-28","cited_by_count":0,"area":"safety"},{"id":"2604.27426","title":"Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors","created":"2026-04-30","cited_by_count":0,"area":"safety"},{"id":"2605.02255","title":"On the Privacy of LLMs: An Ablation Study","created":"2026-05-04","cited_by_count":0,"area":"rag"},{"id":"2605.26795","title":"What Does Chain-of-Thought Contribute at Probe Time? Evidence for Local Co-Occurrence Activation","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2606.00654","title":"The Invitation Trap: Proactive Availability Backdoor in LLMs via Conversational Induction","created":"2026-05-30","cited_by_count":0,"area":"safety"},{"id":"2606.23884","title":"One Year Later...The Harms Persist, But So Do We!","created":"2026-06-22","cited_by_count":0,"area":"safety"},{"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":"2608.28389","title":"CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents","created":"2026-08-28","cited_by_count":0,"area":"rag"},{"id":"2609.13731","title":"Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges","created":"2026-09-12","cited_by_count":0,"area":"agents"},{"id":"2609.23894","title":"Connecting the Dots in Agentic AI Security: A Cross-Dimensional Threat Taxonomy, Evaluation Maturity, and Open Challenges","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.26184","title":"Silent Sabotage: Internal State Triggered Backdoor Attacks on LLM-Powered Robotic Systems","created":"2026-09-02","cited_by_count":0,"area":"safety"},{"id":"2609.27763","title":"Alignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2610.06049","title":"Backdooring Sparse Autoencoders","created":"2026-10-05","cited_by_count":0,"area":"safety"},{"id":"2610.13267","title":"Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}