{"total":59,"rows":[{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"id":"2502.13172","title":"Unveiling Privacy Risks in LLM Agent Memory","created":"2025-02-17","cited_by_count":101,"area":"agents"},{"id":"2408.02544","title":"Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions","created":"2024-08-05","cited_by_count":56,"area":"mllm"},{"id":"2311.00288","title":"Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks","created":"2023-11-01","cited_by_count":55,"area":null},{"id":"2502.16580","title":"Can Indirect Prompt Injection Attacks Be Detected and Removed?","created":"2025-02-23","cited_by_count":52,"area":"safety"},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2411.00459","title":"Defense Against Prompt Injection Attack by Leveraging Attack Techniques","created":"2024-11-01","cited_by_count":40,"area":"safety"},{"id":"2311.09447","title":"How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities","created":"2023-11-15","cited_by_count":33,"area":null},{"id":"2410.08811","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","created":"2024-10-11","cited_by_count":33,"area":"safety"},{"id":"2406.13439","title":"Finding Blind Spots in Evaluator LLMs with Interpretable Checklists","created":"2024-06-19","cited_by_count":32,"area":null},{"id":"2502.12197","title":"A Closer Look at System Prompt Robustness","created":"2025-02-15","cited_by_count":32,"area":"safety"},{"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,"area":"rag"},{"id":"2402.00898","title":"An Early Categorization of Prompt Injection Attacks on Large Language Models","created":"2024-01-31","cited_by_count":30,"area":"safety"},{"id":"2503.04550","title":"Benchmarking Reasoning Robustness in Large Language Models","created":"2025-03-06","cited_by_count":30,"area":"lr"},{"id":"2602.11348","title":"AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition","created":"2026-02-11","cited_by_count":23,"area":"agents"},{"id":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","cited_by_count":21,"area":null},{"id":"2507.13686","title":"TopicAttack: An Indirect Prompt Injection Attack via Topic Transition","created":"2025-07-18","cited_by_count":17,"area":"safety"},{"id":"2406.06737","title":"Raccoon: Prompt Extraction Benchmark of LLM-Integrated Applications","created":"2024-06-10","cited_by_count":16,"area":null},{"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,"area":"safety"},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2502.01349","title":"Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendations","created":"2025-02-03","cited_by_count":11,"area":null},{"id":"2604.15415","title":"HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?","created":"2026-04-16","cited_by_count":11,"area":"agents"},{"id":"2506.00751","title":"Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?","created":"2025-05-31","cited_by_count":10,"area":"alignment"},{"id":"2602.07398","title":"AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management","created":"2026-02-07","cited_by_count":10,"area":"agents"},{"id":"2505.14412","title":"PRL: Prompts from Reinforcement Learning","created":"2025-05-20","cited_by_count":9,"area":"lr"},{"id":"2410.09097","title":"Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations","created":"2024-10-09","cited_by_count":8,"area":"safety"},{"id":"2411.07240","title":"UTMath: Math Evaluation with Unit Test via Reasoning-to-Coding Thoughts","created":"2024-11-11","cited_by_count":8,"area":"lr"},{"id":"2503.13413","title":"DLPO: Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Learning Perspective","created":"2025-03-17","cited_by_count":8,"area":"lr"},{"id":"2505.14368","title":"From ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMs","created":"2025-05-20","cited_by_count":6,"area":"safety"},{"id":"2511.04694","title":"Reasoning Up the Instruction Ladder for Controllable Language Models","created":"2025-10-30","cited_by_count":5,"area":"lr"},{"id":"2511.06890","title":"EduGuardBench: A Holistic Benchmark for Evaluating the Pedagogical Fidelity and Adversarial Safety of LLMs as Simulated Teachers","created":"2025-11-10","cited_by_count":5,"area":"safety"},{"id":"2507.18203","title":"Exploring the Impact of Instruction-Tuning on LLM's Susceptibility to Misinformation","created":"2025-07-24","cited_by_count":4,"area":"safety"},{"id":"2508.13214","title":"Too Easily Fooled? Prompt Injection Breaks LLMs on Frustratingly Simple Multiple-Choice Questions","created":"2025-08-16","cited_by_count":4,"area":"safety"},{"id":"2601.17789","title":"Neuro-Symbolic Verification on Instruction Following of LLMs","created":"2026-01-25","cited_by_count":4,"area":null},{"id":"2609.30243","title":"JevOut: Natural Context Can Flip Decision Models","created":"2026-09-24","cited_by_count":4,"area":null},{"id":"2510.03705","title":"Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods","created":"2025-10-04","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":"2409.01909","title":"LUK: Empowering Log Understanding with Expert Knowledge from Large Language Models","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2504.01048","title":"How does Watermarking Affect Visual Language Models in Document Understanding?","created":"2025-04-01","cited_by_count":2,"area":"mllm"},{"id":"2504.05689","title":"Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators","created":"2025-04-08","cited_by_count":2,"area":"safety"},{"id":"2506.10095","title":"When Meaning Stays the Same, but Models Drift: Evaluating Quality of Service under Token-Level Behavioral Instability in LLMs","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2512.14278","title":"The Trust in AI-Generated Health Advice (TAIGHA) Scale and Short Version (TAIGHA-S): Development and Validation Study","created":"2025-12-16","cited_by_count":1,"area":null},{"id":"2603.03298","title":"TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.05772","title":"Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads","created":"2026-03-06","cited_by_count":1,"area":"safety"},{"id":"2603.21373","title":"PLR: Plackett-Luce for Reordering In-Context Learning Examples","created":"2026-03-22","cited_by_count":1,"area":null},{"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,"area":"rag"},{"id":"2606.03090","title":"\"**Important** You should give me full credits!\": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems","created":"2026-06-02","cited_by_count":1,"area":"safety"},{"id":"2608.02110","title":"IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent Fluctuations","created":"2026-08-03","cited_by_count":1,"area":"deeprl"},{"id":"2608.28411","title":"LongPIBench: A Long-Context Benchmark for Prompt Injection","created":"2026-08-28","cited_by_count":1,"area":"safety"},{"id":"2506.21573","title":"Instruction Learning Paradigms: A Dual Perspective on White-box and Black-box LLMs","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2511.21438","title":"Conversational No-code, Multi-agentic Disease Module Identification and Drug Repurposing Prediction with ChatDRex","created":"2025-11-26","cited_by_count":0,"area":"agents"},{"id":"2512.24415","title":"Language Model Agents Under Attack: A Cross Model-Benchmark of Profit-Seeking Behaviors in Customer Service","created":"2025-12-30","cited_by_count":0,"area":"agents"},{"id":"2603.29418","title":"Covert Visual Prompt Injection against Commercial Multimodal Large Language Models","created":"2026-03-31","cited_by_count":0,"area":"mllm"},{"id":"2605.11664","title":"Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis","created":"2026-05-12","cited_by_count":0,"area":"agents"},{"id":"2605.20654","title":"REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2607.23545","title":"Language Shapes Instruction Hierarchy Compliance in Multilingual LLMs","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2609.11082","title":"ToxicRAG: Compromising Retrieval-Augmented Generation Systems via Single-Shot Knowledge Poisoning Attacks","created":"2026-09-10","cited_by_count":0,"area":"rag"},{"id":"2609.15013","title":"Overflip: Repetition-Induced Label Flips in Guardrail Models","created":"2026-09-14","cited_by_count":0,"area":"safety"},{"id":"2610.02793","title":"PAPER2LLM++: Continual Self-Evolution of LLMs from Research Papers","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}