{"list":"other","total":75,"rows":[{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"id":"2407.12784","title":"AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases","created":"2024-07-17","cited_by_count":429},{"id":"2305.12295","title":"Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning","created":"2023-05-20","cited_by_count":391},{"id":"2410.02644","title":"Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents","created":"2024-10-03","cited_by_count":369},{"id":"2401.11817","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","created":"2024-01-22","cited_by_count":332},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269},{"id":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244},{"id":"2111.02840","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","created":"2021-11-04","cited_by_count":232},{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230},{"id":"2503.18666","title":"AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents","created":"2025-03-24","cited_by_count":223},{"id":"2509.04664","title":"Why Language Models Hallucinate","created":"2025-09-04","cited_by_count":220},{"id":"1708.08689","title":"Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization","created":"2017-08-29","cited_by_count":197},{"id":"2310.19156","title":"Poisoning Retrieval Corpora by Injecting Adversarial Passages","created":"2023-10-29","cited_by_count":159},{"id":"2403.06634","title":"Stealing Part of a Production Language Model","created":"2024-03-11","cited_by_count":159},{"id":"2503.22738","title":"ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning","created":"2025-03-26","cited_by_count":151},{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149},{"id":"2503.03704","title":"Memory Injection Attacks on LLM Agents via Query-Only Interaction","created":"2025-03-05","cited_by_count":144},{"id":"2504.11358","title":"DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks","created":"2025-04-15","cited_by_count":143},{"id":"2410.06703","title":"ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents","created":"2024-10-09","cited_by_count":133},{"id":"2407.19354","title":"The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies","created":"2024-07-28","cited_by_count":131},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126},{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126},{"id":"2406.09187","title":"GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning","created":"2024-06-13","cited_by_count":124},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123},{"id":"2507.15219","title":"PromptArmor: Simple yet Effective Prompt Injection Defenses","created":"2025-07-21","cited_by_count":108},{"id":"2502.13172","title":"Unveiling Privacy Risks in LLM Agent Memory","created":"2025-02-17","cited_by_count":101},{"id":"2402.04049","title":"Systematic Biases in LLM Simulations of Debates","created":"2024-02-06","cited_by_count":99},{"id":"2412.16682","title":"The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents","created":"2024-12-21","cited_by_count":99},{"id":"2003.12909","title":"Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning","created":"2020-03-28","cited_by_count":81},{"id":"2601.10156","title":"ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback","created":"2026-01-15","cited_by_count":72},{"id":"2006.14026","title":"Subpopulation Data Poisoning Attacks","created":"2020-06-24","cited_by_count":70},{"id":"2407.14057","title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference","created":"2024-07-19","cited_by_count":70},{"id":"2508.14925","title":"MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers","created":"2025-08-19","cited_by_count":66},{"id":"2307.08487","title":"Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models","created":"2023-07-17","cited_by_count":60},{"id":"2508.15310","title":"IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents","created":"2025-08-21","cited_by_count":54},{"id":"2305.06972","title":"Spear Phishing With Large Language Models","created":"2023-05-11","cited_by_count":52},{"id":"2410.02584","title":"Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions","created":"2024-10-03","cited_by_count":51},{"id":"2508.01249","title":"AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection","created":"2025-08-02","cited_by_count":46},{"id":"2409.01380","title":"Membership Inference Attacks Against In-Context Learning","created":"2024-09-02","cited_by_count":43},{"id":"2505.05849","title":"AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents","created":"2025-05-09","cited_by_count":42},{"id":"2411.00459","title":"Defense Against Prompt Injection Attack by Leveraging Attack Techniques","created":"2024-11-01","cited_by_count":40},{"id":"2506.09443","title":"LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge","created":"2025-06-11","cited_by_count":37},{"id":"2410.10760","title":"Denial-of-Service Poisoning Attacks against Large Language Models","created":"2024-10-14","cited_by_count":35},{"id":"2412.13879","title":"Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings","created":"2024-12-18","cited_by_count":35},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34},{"id":"2402.04013","title":"Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses","created":"2024-02-06","cited_by_count":30},{"id":"2405.14023","title":"WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response","created":"2024-05-22","cited_by_count":29},{"id":"2601.04170","title":"Agent Drift: Quantifying Behavioral Degradation in Multi-Agent LLM Systems Over Extended Interactions","created":"2026-01-07","cited_by_count":28},{"id":"2408.00523","title":"Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models","created":"2024-08-01","cited_by_count":27},{"id":"2407.06443","title":"Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment","created":"2024-07-08","cited_by_count":25},{"id":"2507.20526","title":"Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition","created":"2025-07-28","cited_by_count":24},{"id":"2512.07086","title":"ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking","created":"2025-12-08","cited_by_count":23},{"id":"2309.10544","title":"Model Leeching: An Extraction Attack Targeting LLMs","created":"2023-09-19","cited_by_count":22},{"id":"2410.21492","title":"FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks","created":"2024-10-28","cited_by_count":22},{"id":"2505.24201","title":"SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems","created":"2025-05-30","cited_by_count":22},{"id":"2506.09956","title":"LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge","created":"2025-06-11","cited_by_count":21},{"id":"2507.15296","title":"Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems","created":"2025-07-21","cited_by_count":18},{"id":"2505.18585","title":"RvLLM: LLM Runtime Verification with Domain Knowledge","created":"2025-05-24","cited_by_count":17},{"id":"2504.20472","title":"Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction","created":"2025-04-29","cited_by_count":16},{"id":"2310.02417","title":"Jailbreaker in Jail: Moving Target Defense for Large Language Models","created":"2023-10-03","cited_by_count":15},{"id":"2507.14987","title":"AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning","created":"2025-07-20","cited_by_count":15},{"id":"2512.06556","title":"Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation","created":"2025-12-06","cited_by_count":13},{"id":"2511.02108","title":"Metamorphic Testing of Large Language Models for Natural Language Processing","created":"2025-11-03","cited_by_count":12},{"id":"2507.08270","title":"Agent Safety Alignment via Reinforcement Learning","created":"2025-07-11","cited_by_count":11},{"id":"2411.13425","title":"Watermark under Fire: A Robustness Evaluation of LLM Watermarking","created":"2024-11-20","cited_by_count":9},{"id":"2411.01222","title":"$B^4$: A Black-Box Scrubbing Attack on LLM Watermarks","created":"2024-11-02","cited_by_count":7},{"id":"2506.20737","title":"MAGPIE: A dataset for Multi-AGent contextual PrIvacy Evaluation","created":"2025-06-25","cited_by_count":6},{"id":"2508.03703","title":"Privacy Risks of LLM-Empowered Recommender Systems: An Inversion Attack Perspective","created":"2025-07-20","cited_by_count":6},{"id":"2510.21946","title":"$\\delta$-STEAL: LLM Stealing Attack with Local Differential Privacy","created":"2025-10-24","cited_by_count":3},{"id":"2507.04478","title":"Model Inversion Attacks on Llama 3: Extracting PII from Large Language Models","created":"2025-07-06","cited_by_count":2}],"next_cursor":null}