{"total":69,"rows":[{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832,"area":null},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2402.06363","title":"StruQ: Defending Against Prompt Injection with Structured Queries","created":"2024-02-09","cited_by_count":375,"area":"safety"},{"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,"area":"agents"},{"id":"2310.12815","title":"Formalizing and Benchmarking Prompt Injection Attacks and Defenses","created":"2023-10-19","cited_by_count":364,"area":"safety"},{"id":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284,"area":"mllm"},{"id":"2402.07867","title":"PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models","created":"2024-02-12","cited_by_count":267,"area":"rag"},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212,"area":"agents"},{"id":"2410.05451","title":"SecAlign: Defending Against Prompt Injection with Preference Optimization","created":"2024-10-07","cited_by_count":210,"area":"alignment"},{"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":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186,"area":"safety"},{"id":"2504.19793","title":"Prompt Injection Attack to Tool Selection in LLM Agents","created":"2025-04-28","cited_by_count":158,"area":"agents"},{"id":"2504.11358","title":"DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks","created":"2025-04-15","cited_by_count":143,"area":"safety"},{"id":"2403.04957","title":"Automatic and Universal Prompt Injection Attacks against Large Language Models","created":"2024-03-07","cited_by_count":119,"area":"safety"},{"id":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82,"area":null},{"id":"2412.03563","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","created":"2024-12-04","cited_by_count":82,"area":"agents"},{"id":"2307.09476","title":"Overthinking the Truth: Understanding how Language Models Process False Demonstrations","created":"2023-07-18","cited_by_count":81,"area":"lr"},{"id":"2402.17840","title":"Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems","created":"2024-02-27","cited_by_count":76,"area":"rag"},{"id":"2401.07612","title":"Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications","created":"2024-01-15","cited_by_count":54,"area":"safety"},{"id":"2402.09674","title":"PAL: Proxy-Guided Black-Box Attack on Large Language Models","created":"2024-02-15","cited_by_count":50,"area":"safety"},{"id":"2307.10719","title":"LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?","created":"2023-07-20","cited_by_count":49,"area":null},{"id":"2311.04235","title":"Can LLMs Follow Simple Rules?","created":"2023-11-06","cited_by_count":46,"area":null},{"id":"2410.22770","title":"InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models","created":"2024-10-30","cited_by_count":42,"area":"safety"},{"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,"area":"safety"},{"id":"2505.18333","title":"A Critical Evaluation of Defenses against Prompt Injection Attacks","created":"2025-05-23","cited_by_count":36,"area":"safety"},{"id":"2401.03315","title":"Malla: Demystifying Real-world Large Language Model Integrated Malicious Services","created":"2024-01-06","cited_by_count":33,"area":null},{"id":"2502.12197","title":"A Closer Look at System Prompt Robustness","created":"2025-02-15","cited_by_count":32,"area":"safety"},{"id":"2502.07586","title":"We Can't Understand AI Using our Existing Vocabulary","created":"2025-02-11","cited_by_count":25,"area":null},{"id":"2406.07954","title":"Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition","created":"2024-06-12","cited_by_count":20,"area":null},{"id":"2510.14005","title":"PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features","created":"2025-10-15","cited_by_count":20,"area":"safety"},{"id":"2505.18135","title":"Tool Preferences in Agentic LLMs are Unreliable","created":"2025-05-23","cited_by_count":18,"area":"agents"},{"id":"2405.14189","title":"Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization","created":"2024-05-23","cited_by_count":16,"area":"safety"},{"id":"2505.00976","title":"Attack and defense techniques in large language models: A survey and new perspectives","created":"2025-05-02","cited_by_count":14,"area":null},{"id":"2212.06295","title":"Despite \"super-human\" performance, current LLMs are unsuited for decisions about ethics and safety","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2506.04202","title":"TracLLM: A Generic Framework for Attributing Long Context LLMs","created":"2025-06-04","cited_by_count":13,"area":null},{"id":"2507.13169","title":"Prompt Injection 2.0: Hybrid AI Threats","created":"2025-07-17","cited_by_count":13,"area":"safety"},{"id":"2401.15545","title":"PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models","created":"2024-01-28","cited_by_count":8,"area":null},{"id":"2406.11007","title":"Threat Modelling and Risk Analysis for Large Language Model (LLM)-Powered Applications","created":"2024-06-16","cited_by_count":8,"area":"safety"},{"id":"2406.00199","title":"Exfiltration of personal information from ChatGPT via prompt injection","created":"2024-05-31","cited_by_count":7,"area":null},{"id":"2409.13331","title":"Applying Pre-trained Multilingual BERT in Embeddings for Improved Malicious Prompt Injection Attacks Detection","created":"2024-09-20","cited_by_count":7,"area":"safety"},{"id":"2508.03793","title":"AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption","created":"2025-08-05","cited_by_count":7,"area":"rag"},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2504.09841","title":"StruPhantom: Evolutionary Injection Attacks on Black-Box Tabular Agents Powered by Large Language Models","created":"2025-04-14","cited_by_count":6,"area":"agents"},{"id":"2410.23182","title":"ProTransformer: Robustify Transformers via Plug-and-Play Paradigm","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2402.12617","title":"Generative AI Security: Challenges and Countermeasures","created":"2024-02-20","cited_by_count":4,"area":null},{"id":"2410.06287","title":"Non-Halting Queries: Exploiting Fixed Points in LLMs","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2505.24613","title":"When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2512.20164","title":"AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2601.10758","title":"Agents at Risk: How Users Unwittingly Undermine LLM Safety","created":"2026-01-14","cited_by_count":3,"area":"agents"},{"id":"2304.12203","title":"Creating Large Language Model Resistant Exams: Guidelines and Strategies","created":"2023-04-18","cited_by_count":2,"area":null},{"id":"2501.09039","title":"Playing Devil's Advocate: Unmasking Toxicity and Vulnerabilities in Large Vision-Language Models","created":"2025-01-14","cited_by_count":2,"area":"mllm"},{"id":"2505.15738","title":"Checkpoint-GCG: Auditing and Attacking Fine-Tuning-Based Prompt Injection Defenses","created":"2025-05-21","cited_by_count":2,"area":"agents"},{"id":"2607.05189","title":"When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents","created":"2026-07-06","cited_by_count":2,"area":"agents"},{"id":"2411.14442","title":"AI Ethics by Design: Implementing Customizable Guardrails for Responsible AI Development","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2507.14202","title":"PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training","created":"2025-07-14","cited_by_count":1,"area":"alignment"},{"id":"2406.11880","title":"Knowledge Return Oriented Prompting (KROP)","created":"2024-06-11","cited_by_count":0,"area":"safety"},{"id":"2510.14365","title":"Understanding the Ability of LLMs to Handle Character-Level Perturbation","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.27140","title":"Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels","created":"2025-10-31","cited_by_count":0,"area":"agents"},{"id":"2511.03128","title":"From Insight to Exploit: Leveraging LLM Collaboration for Adaptive Adversarial Text Generation","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2512.05243","title":"Decoding the Black Box: Discerning AI Rhetorics About and Through Poetic Prompting","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2603.04820","title":"Autoscoring Anticlimax: A Meta-analytic Understanding of AI's Short-answer Shortcomings and Wording Weaknesses","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.02954","title":"LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"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":"2606.19660","title":"A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots","created":"2026-06-17","cited_by_count":0,"area":"safety"},{"id":"2608.07808","title":"The Anatomy of a Prompt Injection: A Component Model for Structured Analysis","created":"2026-08-07","cited_by_count":0,"area":"safety"},{"id":"2608.21656","title":"Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitution","created":"2026-08-21","cited_by_count":0,"area":"rag"},{"id":"2608.28467","title":"Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2610.06401","title":"RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents","created":"2026-10-05","cited_by_count":0,"area":"agents"}],"next_cursor":null}