{"total":85,"rows":[{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194,"area":"safety"},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"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":"2310.15140","title":"AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models","created":"2023-10-23","cited_by_count":111,"area":"alignment"},{"id":"2406.05870","title":"Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents","created":"2024-06-09","cited_by_count":102,"area":"rag"},{"id":"2410.09102","title":"Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy","created":"2024-10-09","cited_by_count":67,"area":"safety"},{"id":"2311.09127","title":"Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts","created":"2023-11-15","cited_by_count":65,"area":"safety"},{"id":"2411.09523","title":"Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents","created":"2024-11-14","cited_by_count":65,"area":"agents"},{"id":"2410.13722","title":"Persistent Pre-Training Poisoning of LLMs","created":"2024-10-17","cited_by_count":48,"area":null},{"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":"2405.15012","title":"Extracting Prompts by Inverting LLM Outputs","created":"2024-05-23","cited_by_count":41,"area":null},{"id":"2504.12680","title":"Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning","created":"2025-04-17","cited_by_count":37,"area":"lr"},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2402.04013","title":"Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses","created":"2024-02-06","cited_by_count":30,"area":null},{"id":"2406.14526","title":"Fantastic Copyrighted Beasts and How (Not) to Generate Them","created":"2024-06-20","cited_by_count":24,"area":null},{"id":"2503.10566","title":"ASIDE: Architectural Separation of Instructions and Data in Language Models","created":"2025-03-13","cited_by_count":24,"area":"safety"},{"id":"2404.16251","title":"Prompt Leakage effect and defense strategies for multi-turn LLM interactions","created":"2024-04-24","cited_by_count":23,"area":null},{"id":"2508.12538","title":"MCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol Security","created":"2025-08-18","cited_by_count":21,"area":"agents"},{"id":"2408.03515","title":"A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems","created":"2024-08-07","cited_by_count":15,"area":"safety"},{"id":"2411.10023","title":"Model Inversion Attacks: A Survey of Approaches and Countermeasures","created":"2024-11-15","cited_by_count":11,"area":null},{"id":"2402.19200","title":"PRSA: Prompt Stealing Attacks against Real-World Prompt Services","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2407.03160","title":"SOS! Soft Prompt Attack Against Open-Source Large Language Models","created":"2024-07-03","cited_by_count":10,"area":"safety"},{"id":"2409.11026","title":"Prompt Obfuscation for Large Language Models","created":"2024-09-17","cited_by_count":10,"area":null},{"id":"2512.08417","title":"Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs","created":"2025-12-09","cited_by_count":10,"area":"agents"},{"id":"2404.13784","title":"Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images","created":"2024-04-21","cited_by_count":9,"area":"mllm"},{"id":"2408.02416","title":"Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models","created":"2024-08-05","cited_by_count":9,"area":null},{"id":"2506.17090","title":"Better Language Model Inversion by Compactly Representing Next-Token Distributions","created":"2025-06-20","cited_by_count":9,"area":null},{"id":"2511.05797","title":"When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins","created":"2025-11-08","cited_by_count":9,"area":"safety"},{"id":"2505.12442","title":"IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems","created":"2025-05-18","cited_by_count":8,"area":"agents"},{"id":"2506.07440","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2408.05061","title":"A Jailbroken GenAI Model Can Cause Substantial Harm: GenAI-powered Applications are Vulnerable to PromptWares","created":"2024-08-09","cited_by_count":7,"area":"safety"},{"id":"2511.00203","title":"Diffusion LLMs are Natural Adversaries for any LLM","created":"2025-10-31","cited_by_count":7,"area":"safety"},{"id":"2410.13691","title":"Jailbreaking LLM-Controlled Robots","created":"2024-10-17","cited_by_count":6,"area":"safety"},{"id":"2507.04531","title":"DP-Fusion: Token-Level Differentially Private Inference for Large Language Models","created":"2025-07-06","cited_by_count":6,"area":"safety"},{"id":"2604.09443","title":"Many-Tier Instruction Hierarchy in LLM Agents","created":"2026-04-10","cited_by_count":6,"area":"agents"},{"id":"2412.13426","title":"PromptKeeper: Safeguarding System Prompts for LLMs","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2508.20282","title":"Network-Level Prompt and Trait Leakage in Local Research Agents","created":"2025-08-27","cited_by_count":5,"area":"agents"},{"id":"2603.15408","title":"TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems","created":"2026-03-16","cited_by_count":5,"area":"agents"},{"id":"2605.28999","title":"Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening","created":"2026-05-27","cited_by_count":5,"area":"safety"},{"id":"2410.12443","title":"Reconstruction of Differentially Private Text Sanitization via Large Language Models","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2412.10807","title":"Towards Action Hijacking of Large Language Model-based Agent","created":"2024-12-14","cited_by_count":4,"area":"agents"},{"id":"2510.08238","title":"Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness","created":"2025-10-09","cited_by_count":4,"area":"agents"},{"id":"2510.14086","title":"Every Language Model Has a Forgery-Resistant Signature","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2512.16059","title":"ContextLeak: Auditing Leakage in Private In-Context Learning Methods","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2601.21233","title":"Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs","created":"2026-01-29","cited_by_count":4,"area":"agents"},{"id":"2607.25560","title":"Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectories","created":"2026-07-28","cited_by_count":4,"area":null},{"id":"2309.04858","title":"Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System","created":"2023-09-09","cited_by_count":3,"area":null},{"id":"2502.09974","title":"Has My System Prompt Been Used? Large Language Model Prompt Membership Inference","created":"2025-02-14","cited_by_count":3,"area":"safety"},{"id":"2502.12630","title":"Automating Prompt Leakage Attacks on Large Language Models Using Agentic Approach","created":"2025-02-18","cited_by_count":3,"area":"agents"},{"id":"2508.19980","title":"Evaluating Language Model Reasoning about Confidential Information","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2406.02481","title":"Large Language Models as Carriers of Hidden Messages","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2409.20135","title":"Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models","created":"2024-09-30","cited_by_count":2,"area":null},{"id":"2502.15902","title":"IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2602.14374","title":"Differentially Private Retrieval-Augmented Generation","created":"2026-02-16","cited_by_count":2,"area":"rag"},{"id":"2608.04192","title":"Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills","created":"2026-08-04","cited_by_count":2,"area":"agents"},{"id":"2506.19109","title":"Enhancing Security in LLM Applications: A Performance Evaluation of Early Detection Systems","created":"2025-06-23","cited_by_count":1,"area":"safety"},{"id":"2506.23296","title":"Securing AI Systems: A Guide to Known Attacks and Impacts","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2507.01752","title":"Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training","created":"2025-07-02","cited_by_count":1,"area":"safety"},{"id":"2509.05608","title":"BinaryShield: Cross-Service Threat Intelligence in LLM Services using Privacy-Preserving Fingerprints","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2510.12117","title":"Locket: Robust Feature-Locking Technique for Language Models","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2510.17000","title":"Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs","created":"2025-10-19","cited_by_count":1,"area":"safety"},{"id":"2511.08710","title":"Convergence dynamics of Agent-to-Agent Interactions with Misaligned objectives","created":"2025-11-11","cited_by_count":1,"area":"agents"},{"id":"2511.19569","title":"An Invariant Latent Space Perspective on Language Model Inversion","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2601.04666","title":"Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2604.09075","title":"Hierarchical Alignment: Enforcing Hierarchical Instruction-Following in LLMs through Logical Consistency","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2606.03344","title":"RogueMerge: Robust and Unified Attacks against LLM Model Merging","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2607.05120","title":"Agent Data Injection Attacks are Realistic Threats to AI Agents","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2404.07439","title":"Behavior Trees Enable Structured Programming of Language Model Agents","created":"2024-04-11","cited_by_count":0,"area":"agents"},{"id":"2503.12339","title":"A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger Learning","created":"2025-03-16","cited_by_count":0,"area":"safety"},{"id":"2510.15768","title":"On Non-interactive Evaluation of Animal Communication Translators","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2510.22963","title":"When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents","created":"2025-10-27","cited_by_count":0,"area":"agents"},{"id":"2511.16209","title":"PSM: Prompt Sensitivity Minimization via LLM-Guided Black-Box Optimization","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2511.18499","title":"For Those Who May Find Themselves on the Red Team","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2512.03720","title":"Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2602.00911","title":"Synapse: Federated Tool Routing via Typed Compendium Artifacts","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2604.01039","title":"Evaluation and Hardening of LLM System Instructions Against Extraction via Encoding Attacks","created":"2026-04-01","cited_by_count":0,"area":"agents"},{"id":"2605.05818","title":"LeakDojo: Decoding the Leakage Threats of RAG Systems","created":"2026-05-07","cited_by_count":0,"area":"rag"},{"id":"2607.29378","title":"PTP: Previous-Token Prediction based LLM Inversion for Near-Exact Prompt Reconstruction","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.02995","title":"SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels","created":"2026-08-04","cited_by_count":0,"area":"inference"},{"id":"2608.30441","title":"ECLIPSE: Self-Evolving Stealthy Prompt Injection Attack against Long-Horizon Agentic Systems","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.01663","title":"Context Inference Attacks Without Jailbreaks","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.03662","title":"Extracting Forgotten Prompts from Targeted Unlearned Models","created":"2026-09-03","cited_by_count":0,"area":"safety"},{"id":"2609.04533","title":"Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection","created":"2026-09-03","cited_by_count":0,"area":"safety"},{"id":"2609.12808","title":"K-Bench: A Benchmark for LLM Unlearning in Agentic Deployments","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2610.05453","title":"The Poisoned Conversation: Privacy-Leaking Watermarks in Unified Multimodal Models","created":"2026-10-04","cited_by_count":0,"area":"safety"}],"next_cursor":null}