{"total":189,"rows":[{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651,"area":"alignment"},{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489,"area":"safety"},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"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":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2307.01850","title":"Self-Consuming Generative Models Go MAD","created":"2023-07-04","cited_by_count":250,"area":null},{"id":"2312.06942","title":"AI Control: Improving Safety Despite Intentional Subversion","created":"2023-12-12","cited_by_count":229,"area":"safety"},{"id":"2310.05189","title":"Factuality Challenges in the Era of Large Language Models","created":"2023-10-08","cited_by_count":126,"area":null},{"id":"2402.07510","title":"Secret Collusion among AI Agents: Multi-Agent Deception via Steganography","created":"2024-02-12","cited_by_count":113,"area":"agents"},{"id":"2310.06356","title":"A Semantic Invariant Robust Watermark for Large Language Models","created":"2023-10-10","cited_by_count":112,"area":"safety"},{"id":"2310.14724","title":"A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions","created":"2023-10-23","cited_by_count":105,"area":null},{"id":"2310.05914","title":"NEFTune: Noisy Embeddings Improve Instruction Finetuning","created":"2023-10-09","cited_by_count":100,"area":null},{"id":"2402.19361","title":"Watermark Stealing in Large Language Models","created":"2024-02-29","cited_by_count":92,"area":"safety"},{"id":"2308.14840","title":"Identifying and Mitigating the Security Risks of Generative AI","created":"2023-08-28","cited_by_count":91,"area":null},{"id":"2311.04378","title":"Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models","created":"2023-11-07","cited_by_count":87,"area":"safety"},{"id":"2308.00113","title":"Three Bricks to Consolidate Watermarks for Large Language Models","created":"2023-07-26","cited_by_count":84,"area":"safety"},{"id":"2312.04469","title":"On the Learnability of Watermarks for Language Models","created":"2023-12-07","cited_by_count":81,"area":"safety"},{"id":"2310.12362","title":"REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models","created":"2023-10-18","cited_by_count":78,"area":"safety"},{"id":"2401.13927","title":"Adaptive Text Watermark for Large Language Models","created":"2024-01-25","cited_by_count":67,"area":"safety"},{"id":"2310.18512","title":"Preventing Language Models From Hiding Their Reasoning","created":"2023-10-27","cited_by_count":65,"area":"lr"},{"id":"2402.14904","title":"Watermarking Makes Language Models Radioactive","created":"2024-02-22","cited_by_count":58,"area":"safety"},{"id":"2308.00221","title":"Advancing Beyond Identification: Multi-bit Watermark for Large Language Models","created":"2023-08-01","cited_by_count":57,"area":"safety"},{"id":"2307.15992","title":"Towards Codable Watermarking for Injecting Multi-bits Information to LLMs","created":"2023-07-29","cited_by_count":54,"area":"safety"},{"id":"2403.04808","title":"WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off","created":"2024-03-06","cited_by_count":54,"area":"safety"},{"id":"2411.18479","title":"SoK: Watermarking for AI-Generated Content","created":"2024-11-27","cited_by_count":51,"area":"safety"},{"id":"2402.16187","title":"No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices","created":"2024-02-25","cited_by_count":50,"area":"safety"},{"id":"2401.16820","title":"Provably Robust Multi-bit Watermarking for AI-generated Text","created":"2024-01-30","cited_by_count":47,"area":"safety"},{"id":"2402.09370","title":"Pseudorandom Error-Correcting Codes","created":"2024-02-14","cited_by_count":44,"area":"safety"},{"id":"2402.02333","title":"Copyright Protection in Generative AI: A Technical Perspective","created":"2024-02-04","cited_by_count":38,"area":null},{"id":"2405.07932","title":"PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition","created":"2024-05-13","cited_by_count":35,"area":"safety"},{"id":"2402.18059","title":"Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models","created":"2024-02-28","cited_by_count":34,"area":"safety"},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2502.06872","title":"Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey","created":"2025-02-08","cited_by_count":30,"area":"rag"},{"id":"2310.08920","title":"Embarrassingly Simple Text Watermarks","created":"2023-10-13","cited_by_count":29,"area":"safety"},{"id":"2310.15264","title":"Towards Possibilities & Impossibilities of AI-generated Text Detection: A Survey","created":"2023-10-23","cited_by_count":28,"area":null},{"id":"2312.07930","title":"Towards Optimal Statistical Watermarking","created":"2023-12-13","cited_by_count":26,"area":"safety"},{"id":"2409.08087","title":"Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks","created":"2024-09-12","cited_by_count":26,"area":"safety"},{"id":"2312.17295","title":"Optimizing watermarks for large language models","created":"2023-12-28","cited_by_count":25,"area":"safety"},{"id":"2410.07959","title":"COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act","created":"2024-10-10","cited_by_count":24,"area":null},{"id":"2405.20777","title":"Black-Box Detection of Language Model Watermarks","created":"2024-05-28","cited_by_count":23,"area":"safety"},{"id":"2409.00089","title":"Watermarking Techniques for Large Language Models: A Survey","created":"2024-08-26","cited_by_count":23,"area":"safety"},{"id":"2403.10553","title":"Learning to Watermark LLM-generated Text via Reinforcement Learning","created":"2024-03-13","cited_by_count":22,"area":"safety"},{"id":"2410.02890","title":"Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach","created":"2024-10-03","cited_by_count":22,"area":"safety"},{"id":"2402.14883","title":"Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning","created":"2024-02-22","cited_by_count":21,"area":"safety"},{"id":"2310.00833","title":"Necessary and Sufficient Watermark for Large Language Models","created":"2023-10-02","cited_by_count":19,"area":"safety"},{"id":"2411.11203","title":"Debiasing Watermarks for Large Language Models via Maximal Coupling","created":"2024-11-17","cited_by_count":19,"area":"safety"},{"id":"2405.11109","title":"Watermarking Language Models for Many Adaptive Users","created":"2024-05-17","cited_by_count":18,"area":"safety"},{"id":"2501.17858","title":"Improving Your Model Ranking on Chatbot Arena by Vote Rigging","created":"2025-01-29","cited_by_count":17,"area":null},{"id":"2410.02099","title":"A Watermark for Black-Box Language Models","created":"2024-10-02","cited_by_count":16,"area":"safety"},{"id":"2410.02440","title":"Optimizing Adaptive Attacks against Watermarks for Language Models","created":"2024-10-03","cited_by_count":16,"area":"safety"},{"id":"2410.03537","title":"Ward: Provable RAG Dataset Inference via LLM Watermarks","created":"2024-10-04","cited_by_count":16,"area":"safety"},{"id":"2506.16349","title":"Watermarking Autoregressive Image Generation","created":"2025-06-19","cited_by_count":16,"area":"safety"},{"id":"2310.05030","title":"Counter Turing Test CT^2: AI-Generated Text Detection is Not as Easy as You May Think -- Introducing AI Detectability Index","created":"2023-10-08","cited_by_count":14,"area":"lr"},{"id":"2410.13805","title":"A Watermark for Order-Agnostic Language Models","created":"2024-10-17","cited_by_count":14,"area":"safety"},{"id":"2410.13808","title":"De-mark: Watermark Removal in Large Language Models","created":"2024-10-17","cited_by_count":14,"area":"safety"},{"id":"2406.02633","title":"Edit Distance Robust Watermarks via Indexing Pseudorandom Codes","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2406.04662","title":"Evaluating and Mitigating IP Infringement in Visual Generative AI","created":"2024-06-07","cited_by_count":13,"area":null},{"id":"2410.03168","title":"Can Watermarked LLMs be Identified by Users via Crafted Prompts?","created":"2024-10-04","cited_by_count":13,"area":"safety"},{"id":"2502.10525","title":"Towards Watermarking of Open-Source LLMs","created":"2025-02-14","cited_by_count":13,"area":"safety"},{"id":"2502.05240","title":"Survey on AI-Generated Media Detection: From Non-MLLM to MLLM","created":"2025-02-07","cited_by_count":12,"area":null},{"id":"2506.05502","title":"StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models","created":"2025-06-05","cited_by_count":12,"area":"safety"},{"id":"2510.17489","title":"DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning","created":"2025-10-20","cited_by_count":12,"area":null},{"id":"2312.02382","title":"New Evaluation Metrics Capture Quality Degradation due to LLM Watermarking","created":"2023-12-04","cited_by_count":11,"area":"safety"},{"id":"2402.16578","title":"Multi-Bit Distortion-Free Watermarking for Large Language Models","created":"2024-02-26","cited_by_count":11,"area":"safety"},{"id":"2504.17480","title":"Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation","created":"2025-04-24","cited_by_count":11,"area":"safety"},{"id":"2309.07689","title":"Detecting ChatGPT: A Survey of the State of Detecting ChatGPT-Generated Text","created":"2023-09-14","cited_by_count":10,"area":null},{"id":"2509.24368","title":"Watermarking Diffusion Language Models","created":"2025-09-29","cited_by_count":10,"area":"diffusion"},{"id":"2505.08878","title":"Optimized Couplings for Watermarking Large Language Models","created":"2025-05-13","cited_by_count":9,"area":"safety"},{"id":"2505.16723","title":"LLM Fingerprinting via Semantically Conditioned Watermarks","created":"2025-05-22","cited_by_count":9,"area":"safety"},{"id":"2507.06274","title":"Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks","created":"2025-07-08","cited_by_count":9,"area":"safety"},{"id":"2509.09112","title":"Character-Level Perturbations Disrupt LLM Watermarks","created":"2025-09-11","cited_by_count":9,"area":"safety"},{"id":"2310.07726","title":"Warfare:Breaking the Watermark Protection of AI-Generated Content","created":"2023-09-27","cited_by_count":8,"area":"safety"},{"id":"2410.20418","title":"Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models","created":"2024-10-27","cited_by_count":8,"area":"inference"},{"id":"2504.13416","title":"STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings","created":"2025-04-18","cited_by_count":8,"area":null},{"id":"2506.01011","title":"Autoregressive Images Watermarking through Lexical Biasing: An Approach Resistant to Regeneration Attack","created":"2025-06-01","cited_by_count":8,"area":"safety"},{"id":"2405.06331","title":"LMD3: Language Model Data Density Dependence","created":"2024-05-10","cited_by_count":7,"area":null},{"id":"2409.09739","title":"PersonaMark: Personalized LLM watermarking for model protection and user attribution","created":"2024-09-15","cited_by_count":7,"area":"safety"},{"id":"2504.02458","title":"Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendation","created":"2025-04-03","cited_by_count":7,"area":"rag"},{"id":"2605.10977","title":"PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks","created":"2026-05-09","cited_by_count":7,"area":"safety"},{"id":"2405.13517","title":"WaterPool: A Watermark Mitigating Trade-offs among Imperceptibility, Efficacy and Robustness","created":"2024-05-22","cited_by_count":6,"area":null},{"id":"2409.14285","title":"ESPERANTO: Evaluating Synthesized Phrases to Enhance Robustness in AI Detection for Text Origination","created":"2024-09-22","cited_by_count":6,"area":null},{"id":"2410.02693","title":"Discovering Spoofing Attempts on Language Model Watermarks","created":"2024-10-03","cited_by_count":6,"area":"safety"},{"id":"2410.03600","title":"Efficiently Identifying Watermarked Segments in Mixed-Source Texts","created":"2024-10-04","cited_by_count":6,"area":"safety"},{"id":"2502.17259","title":"Detecting Benchmark Contamination Through Watermarking","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2310.01297","title":"Co-audit: tools to help humans double-check AI-generated content","created":"2023-10-02","cited_by_count":5,"area":null},{"id":"2311.07700","title":"AuthentiGPT: Detecting Machine-Generated Text via Black-Box Language Models Denoising","created":"2023-11-13","cited_by_count":5,"area":null},{"id":"2407.11100","title":"Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond","created":"2024-07-15","cited_by_count":5,"area":"safety"},{"id":"2509.07287","title":"Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2509.24048","title":"Analyzing and Evaluating Unbiased Language Model Watermark","created":"2025-09-28","cited_by_count":5,"area":"safety"},{"id":"2603.11784","title":"Language Generation with Replay: A Learning-Theoretic View of Model Collapse","created":"2026-03-12","cited_by_count":5,"area":"synth"},{"id":"2605.11036","title":"Sequential Behavioral Watermarking for LLM Agents","created":"2026-05-11","cited_by_count":5,"area":"agents"},{"id":"2605.12456","title":"TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection","created":"2026-05-12","cited_by_count":5,"area":"safety"},{"id":"2607.08400","title":"TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectories","created":"2026-07-09","cited_by_count":5,"area":"agents"},{"id":"2312.01523","title":"SymNoise: Advancing Language Model Fine-tuning with Symmetric Noise","created":"2023-12-03","cited_by_count":4,"area":null},{"id":"2405.08400","title":"Stylometric Watermarks for Large Language Models","created":"2024-05-14","cited_by_count":4,"area":"safety"},{"id":"2407.04794","title":"On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks","created":"2024-07-05","cited_by_count":4,"area":"safety"},{"id":"2410.20670","title":"Segmenting Watermarked Texts From Language Models","created":"2024-10-28","cited_by_count":4,"area":"safety"},{"id":"2412.03107","title":"CredID: Credible Multi-Bit Watermark for Large Language Models Identification","created":"2024-12-04","cited_by_count":4,"area":"safety"},{"id":"2505.02344","title":"An End-to-End Model for Logits-Based Large Language Models Watermarking","created":"2025-05-05","cited_by_count":4,"area":"safety"},{"id":"2507.07871","title":"Mitigating Watermark Forgery in Generative Models via Randomized Key Selection","created":"2025-07-10","cited_by_count":4,"area":"safety"}],"next_cursor":"100"}