{"total":58,"rows":[{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2409.19798","title":"Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data","created":"2024-09-29","cited_by_count":50,"area":"safety"},{"id":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"area":"agents"},{"id":"2504.13146","title":"Antidistillation Sampling","created":"2025-04-17","cited_by_count":25,"area":null},{"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":"2502.07760","title":"Scalable Fingerprinting of Large Language Models","created":"2025-02-11","cited_by_count":14,"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":"2410.18861","title":"Provably Robust Watermarks for Open-Source Language Models","created":"2024-10-24","cited_by_count":13,"area":"safety"},{"id":"2505.23847","title":"Seven Security Challenges in Cross-domain Multi-agent LLM Systems","created":"2025-05-28","cited_by_count":12,"area":"agents"},{"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":"2509.26404","title":"SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From","created":"2025-09-30","cited_by_count":10,"area":null},{"id":"2505.16723","title":"LLM Fingerprinting via Semantically Conditioned Watermarks","created":"2025-05-22","cited_by_count":9,"area":"safety"},{"id":"2504.13416","title":"STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings","created":"2025-04-18","cited_by_count":8,"area":null},{"id":"2510.18333","title":"Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption","created":"2025-10-21","cited_by_count":7,"area":"safety"},{"id":"2502.17259","title":"Detecting Benchmark Contamination Through Watermarking","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2506.23731","title":"Radioactive Watermarks in Diffusion and Autoregressive Image Generative Models","created":"2025-06-30","cited_by_count":6,"area":"safety"},{"id":"2602.03812","title":"Antidistillation Fingerprinting","created":"2026-02-03","cited_by_count":6,"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":"2502.15010","title":"Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models","created":"2025-02-20","cited_by_count":5,"area":"safety"},{"id":"2506.21209","title":"BitMark: Watermarking Bitwise Autoregressive Image Generative Models","created":"2025-06-26","cited_by_count":5,"area":"safety"},{"id":"2510.02962","title":"Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking","created":"2025-10-03","cited_by_count":5,"area":"safety"},{"id":"2510.10161","title":"Large Language Model Sourcing: A Survey","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2605.12456","title":"TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection","created":"2026-05-12","cited_by_count":5,"area":"safety"},{"id":"2510.09655","title":"Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique","created":"2025-10-07","cited_by_count":4,"area":null},{"id":"2510.12119","title":"ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation","created":"2025-10-14","cited_by_count":4,"area":"safety"},{"id":"2510.23891","title":"PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs","created":"2025-10-27","cited_by_count":4,"area":"safety"},{"id":"2602.18700","title":"Watermarking LLM Agent Trajectories","created":"2026-02-21","cited_by_count":4,"area":"agents"},{"id":"2506.04462","title":"Watermarking Degrades Alignment in Language Models: Analysis and Mitigation","created":"2025-06-04","cited_by_count":3,"area":"alignment"},{"id":"2606.10813","title":"RedAct: Redacting Agent Capability Traces for Procedural Skill Protection","created":"2026-06-09","cited_by_count":3,"area":"safety"},{"id":"2509.20924","title":"RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks","created":"2025-09-25","cited_by_count":2,"area":"safety"},{"id":"2512.16904","title":"How Good is Post-Hoc Watermarking With Language Model Rephrasing?","created":"2025-12-18","cited_by_count":2,"area":"safety"},{"id":"2605.16462","title":"Asking Back: Interaction-Layer Antidistillation Watermarks","created":"2026-05-15","cited_by_count":2,"area":"distill"},{"id":"2505.05712","title":"LLM-Text Watermarking based on Lagrange Interpolation","created":"2025-05-09","cited_by_count":1,"area":"safety"},{"id":"2506.06409","title":"HeavyWater and SimplexWater: Distortion-Free LLM Watermarks for Low-Entropy Next-Token Predictions","created":"2025-06-06","cited_by_count":1,"area":"safety"},{"id":"2510.04966","title":"ActiveMark: on watermarking of visual foundation models via massive activations","created":"2025-10-06","cited_by_count":1,"area":"safety"},{"id":"2605.18829","title":"Lossless Anti-Distillation Sampling","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.23175","title":"Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection","created":"2026-05-22","cited_by_count":1,"area":"safety"},{"id":"2607.13003","title":"Watermark Forensics for Generative Models: An Information-Theoretic Perspective","created":"2026-07-14","cited_by_count":1,"area":"safety"},{"id":"2503.20800","title":"Evidencing Unauthorized Training Data from AI Generated Content using Information Isotopes","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2602.12630","title":"TensorCommitments: A Lightweight Verifiable Inference for Language Models","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.10695","title":"RandMark: On Random Watermarking of Visual Foundation Models","created":"2026-03-11","cited_by_count":0,"area":"safety"},{"id":"2603.13396","title":"SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation","created":"2026-03-11","cited_by_count":0,"area":"diffusion"},{"id":"2603.18793","title":"Functional Subspace Watermarking for Large Language Models","created":"2026-03-19","cited_by_count":0,"area":"safety"},{"id":"2605.06596","title":"FedAttr: Towards Privacy-preserving Client-Level Attribution in Federated LLM Fine-tuning","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2605.08964","title":"Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents","created":"2026-05-09","cited_by_count":0,"area":"agents"},{"id":"2605.14283","title":"Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games","created":"2026-05-14","cited_by_count":0,"area":"agents"},{"id":"2606.17123","title":"LineageMark: Multi-user White-box Watermarking for Contribution Tracing in Model Derivation Chains","created":"2026-06-15","cited_by_count":0,"area":"safety"},{"id":"2606.21045","title":"OVIG: Optimistic Verification of AI Training Integrity via Gradient Signals","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.00325","title":"Watermarking for Proprietary Dataset Protection","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.13541","title":"When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.16648","title":"Synchronization-Free Algebraic Fingerprints for Large Language Models: From Autoregressive to Diffusion Models","created":"2026-07-18","cited_by_count":0,"area":"safety"},{"id":"2608.29151","title":"WoE Wrote It? Watermarking Mixture-of-Experts LLMs for Black-Box Text Provenance","created":"2026-08-29","cited_by_count":0,"area":"safety"},{"id":"2609.11149","title":"Break Step: Recursive Training Resonates with Replayed Sampling Noise","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.32749","title":"Retrospective Distillation Attribution via Normalized Response Similarity","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.35881","title":"GenoTrace: Inheritable Watermarks for Genome Foundation Model Distillation","created":"2026-09-27","cited_by_count":0,"area":"safety"},{"id":"2610.15685","title":"Radioactive Feedback: Tracing Models Trained by Label-Only LLM Supervision","created":"2026-10-11","cited_by_count":0,"area":"distill"},{"id":"2610.18517","title":"Imprinting: Knowledge Distillation Can Shift Student Behavior","created":"2026-10-13","cited_by_count":0,"area":"distill"}],"next_cursor":null}