{"total":99,"rows":[{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":538,"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":411,"area":null},{"id":"2305.20086","title":"Understanding and Mitigating Copying in Diffusion Models","created":"2023-05-31","cited_by_count":210,"area":"diffusion"},{"id":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116,"area":null},{"id":"2402.09910","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","created":"2024-02-15","cited_by_count":75,"area":null},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":74,"area":null},{"id":"2308.04430","title":"SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore","created":"2023-08-08","cited_by_count":71,"area":null},{"id":"2311.01797","title":"On the Generalization Properties of Diffusion Models","created":"2023-11-03","cited_by_count":69,"area":"diffusion"},{"id":"2401.05779","title":"Erasing Undesirable Influence in Diffusion Models","created":"2024-01-11","cited_by_count":57,"area":"diffusion"},{"id":"2304.10411","title":"Attention Scheme Inspired Softmax Regression","created":"2023-04-20","cited_by_count":49,"area":null},{"id":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45,"area":null},{"id":"2311.13127","title":"MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning","created":"2023-11-22","cited_by_count":44,"area":"diffusion"},{"id":"2411.00113","title":"A Geometric Framework for Understanding Memorization in Generative Models","created":"2024-10-31","cited_by_count":41,"area":null},{"id":"2402.02333","title":"Copyright Protection in Generative AI: A Technical Perspective","created":"2024-02-04","cited_by_count":40,"area":null},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":38,"area":null},{"id":"2306.08620","title":"Anticipatory Music Transformer","created":"2023-06-14","cited_by_count":36,"area":null},{"id":"2407.07087","title":"CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation","created":"2024-07-09","cited_by_count":35,"area":null},{"id":"2401.04136","title":"The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline","created":"2024-01-07","cited_by_count":33,"area":"diffusion"},{"id":"2306.13384","title":"DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology","created":"2023-06-23","cited_by_count":29,"area":"diffusion"},{"id":"2406.08431","title":"Diffusion Soup: Model Merging for Text-to-Image Diffusion Models","created":"2024-06-12","cited_by_count":27,"area":"diffusion"},{"id":"2308.12247","title":"How to Protect Copyright Data in Optimization of Large Language Models?","created":"2023-08-23","cited_by_count":26,"area":null},{"id":"2505.16959","title":"Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models","created":"2025-05-22","cited_by_count":26,"area":"diffusion"},{"id":"2305.04701","title":"Differentially Private Attention Computation","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2310.14369","title":"MoPe: Model Perturbation-based Privacy Attacks on Language Models","created":"2023-10-22","cited_by_count":25,"area":null},{"id":"2402.14845","title":"Purifying Large Language Models by Ensembling a Small Language Model","created":"2024-02-19","cited_by_count":25,"area":"safety"},{"id":"2305.14822","title":"Can Copyright be Reduced to Privacy?","created":"2023-05-24","cited_by_count":24,"area":null},{"id":"2403.18920","title":"CPR: Retrieval Augmented Generation for Copyright Protection","created":"2024-03-27","cited_by_count":24,"area":"rag"},{"id":"2406.14526","title":"Fantastic Copyrighted Beasts and How (Not) to Generate Them","created":"2024-06-20","cited_by_count":24,"area":null},{"id":"2405.16567","title":"Automatic Jailbreaking of the Text-to-Image Generative AI Systems","created":"2024-05-26","cited_by_count":23,"area":"safety"},{"id":"2504.12532","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","created":"2025-04-16","cited_by_count":23,"area":"diffusion"},{"id":"2508.17689","title":"On the Edge of Memorization in Diffusion Models","created":"2025-08-25","cited_by_count":23,"area":"diffusion"},{"id":"2311.12803","title":"On Copyright Risks of Text-to-Image Diffusion Models","created":"2023-09-15","cited_by_count":20,"area":"diffusion"},{"id":"2406.04327","title":"Causal Estimation of Memorisation Profiles","created":"2024-06-06","cited_by_count":20,"area":null},{"id":"2307.05527","title":"The Ethical Implications of Generative Audio Models: A Systematic Literature Review","created":"2023-07-07","cited_by_count":18,"area":null},{"id":"2307.08045","title":"Beyond Classical Attention: Quantum Attention for Scalable Computation","created":"2023-07-16","cited_by_count":18,"area":null},{"id":"2404.13964","title":"An Economic Solution to Copyright Challenges of Generative AI","created":"2024-04-22","cited_by_count":18,"area":null},{"id":"2407.17417","title":"Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?","created":"2024-07-24","cited_by_count":18,"area":"safety"},{"id":"2308.01937","title":"Training Data Protection with Compositional Diffusion Models","created":"2023-08-02","cited_by_count":17,"area":"diffusion"},{"id":"2502.03435","title":"Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization","created":"2025-02-05","cited_by_count":17,"area":"diffusion"},{"id":"2304.10819","title":"Auditing and Generating Synthetic Data with Controllable Trust Trade-offs","created":"2023-04-21","cited_by_count":13,"area":null},{"id":"2307.02792","title":"What Should Data Science Education Do with Large Language Models?","created":"2023-07-06","cited_by_count":13,"area":null},{"id":"2310.12462","title":"Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights","created":"2023-10-19","cited_by_count":13,"area":null},{"id":"2405.00228","title":"Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion","created":"2024-04-30","cited_by_count":12,"area":null},{"id":"2408.00001","title":"Replication in Visual Diffusion Models: A Survey and Outlook","created":"2024-07-07","cited_by_count":12,"area":"diffusion"},{"id":"2407.21248","title":"Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens","created":"2024-07-30","cited_by_count":11,"area":null},{"id":"2403.17691","title":"Not All Similarities Are Created Equal: Leveraging Data-Driven Biases to Inform GenAI Copyright Disputes","created":"2024-03-26","cited_by_count":10,"area":null},{"id":"2404.06737","title":"Disguised Copyright Infringement of Latent Diffusion Models","created":"2024-04-10","cited_by_count":10,"area":"diffusion"},{"id":"2507.05578","title":"The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation","created":"2025-07-08","cited_by_count":10,"area":"safety"},{"id":"2310.17551","title":"Unpacking the Ethical Value Alignment in Big Models","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2410.19406","title":"An Auditing Test To Detect Behavioral Shift in Language Models","created":"2024-10-25","cited_by_count":9,"area":null},{"id":"2306.08173","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","created":"2023-06-13","cited_by_count":8,"area":null},{"id":"2503.12072","title":"Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models","created":"2025-03-15","cited_by_count":8,"area":null},{"id":"2311.13624","title":"A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer","created":"2023-11-22","cited_by_count":7,"area":null},{"id":"2405.05846","title":"An Inversion-based Measure of Memorization for Diffusion Models","created":"2024-05-09","cited_by_count":7,"area":"diffusion"},{"id":"2406.03341","title":"Tackling Copyright Issues in AI Image Generation Through Originality Estimation and Genericization","created":"2024-06-05","cited_by_count":7,"area":null},{"id":"2406.15386","title":"U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI","created":"2024-04-22","cited_by_count":7,"area":null},{"id":"2412.06619","title":"Copyright-Protected Language Generation via Adaptive Model Fusion","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2307.13527","title":"Not with my name! Inferring artists' names of input strings employed by Diffusion Models","created":"2023-07-25","cited_by_count":6,"area":"diffusion"},{"id":"2404.15697","title":"DeepFeatureX Net: Deep Features eXtractors based Network for discriminating synthetic from real images","created":"2024-04-24","cited_by_count":6,"area":null},{"id":"2412.01528","title":"CopyrightShield: Enhancing Diffusion Model Security against Copyright Infringement Attacks","created":"2024-12-02","cited_by_count":6,"area":"diffusion"},{"id":"2309.07254","title":"Mitigate Replication and Copying in Diffusion Models with Generalized Caption and Dual Fusion Enhancement","created":"2023-09-13","cited_by_count":5,"area":"diffusion"},{"id":"2312.00057","title":"VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2407.13493","title":"Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Law","created":"2024-07-18","cited_by_count":5,"area":null},{"id":"2503.22948","title":"SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning","created":"2025-03-29","cited_by_count":5,"area":"alignment"},{"id":"2404.06077","title":"Is Your AI Truly Yours? Leveraging Blockchain for Copyrights, Provenance, and Lineage","created":"2024-04-09","cited_by_count":4,"area":null},{"id":"2407.20105","title":"Strong Copyright Protection for Language Models via Adaptive Model Fusion","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2408.08184","title":"Not Every Image is Worth a Thousand Words: Quantifying Originality in Stable Diffusion","created":"2024-08-15","cited_by_count":4,"area":"diffusion"},{"id":"2409.19952","title":"Image Copy Detection for Diffusion Models","created":"2024-09-30","cited_by_count":4,"area":"diffusion"},{"id":"2502.15278","title":"CopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion Models","created":"2025-02-21","cited_by_count":4,"area":"diffusion"},{"id":"2406.15916","title":"Credit Attribution and Stable Compression","created":"2024-06-22","cited_by_count":3,"area":null},{"id":"2409.07025","title":"CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion","created":"2024-09-11","cited_by_count":3,"area":"diffusion"},{"id":"2410.24015","title":"Unveiling Synthetic Faces: How Synthetic Datasets Can Expose Real Identities","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2507.22499","title":"LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning","created":"2025-07-30","cited_by_count":3,"area":"safety"},{"id":"2509.00641","title":"AMCR: A Framework for Assessing and Mitigating Copyright Risks in Generative Models","created":"2025-08-31","cited_by_count":3,"area":null},{"id":"2509.22723","title":"Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models","created":"2025-09-25","cited_by_count":3,"area":"diffusion"},{"id":"2306.12609","title":"Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities","created":"2023-06-22","cited_by_count":2,"area":null},{"id":"2312.06646","title":"Computational Copyright: Towards A Royalty Model for Music Generative AI","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2410.00475","title":"Probabilistic Analysis of Copyright Disputes and Generative AI Safety","created":"2024-10-01","cited_by_count":2,"area":null},{"id":"2511.09493","title":"Consensus Sampling for Safer Generative AI","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2602.17168","title":"BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning","created":"2026-02-19","cited_by_count":2,"area":"safety"},{"id":"2605.06077","title":"Understanding diffusion models requires rethinking (again) generalization","created":"2026-05-07","cited_by_count":2,"area":"diffusion"},{"id":"2403.19050","title":"Detecting Generative Parroting through Overfitting Masked Autoencoders","created":"2024-03-27","cited_by_count":1,"area":null},{"id":"2408.13278","title":"Randomization Techniques to Mitigate the Risk of Copyright Infringement","created":"2024-08-21","cited_by_count":1,"area":null},{"id":"2503.16171","title":"Guardians of Generation: Dynamic Inference-Time Copyright Shielding with Adaptive Guidance for AI Image Generation","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2506.15076","title":"Learning-Time Encoding Shapes Unlearning in LLMs","created":"2025-06-18","cited_by_count":1,"area":"safety"},{"id":"2506.19881","title":"Blameless Users in a Clean Room: Defining Copyright Protection for Generative Models","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2511.21600","title":"Robust Spectral Watermark for Synthetic Tabular Data","created":"2025-11-26","cited_by_count":1,"area":"safety"},{"id":"2602.07120","title":"Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2411.14639","title":"Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings","created":"2024-11-22","cited_by_count":0,"area":"diffusion"},{"id":"2503.22782","title":"Patronus: Interpretable Diffusion Models with Prototypes","created":"2025-03-28","cited_by_count":0,"area":"diffusion"},{"id":"2505.23788","title":"Nine Ways to Break Copyright Law and Why Our LLM Won't: A Fair Use Aligned Generation Framework","created":"2025-05-25","cited_by_count":0,"area":"alignment"},{"id":"2602.00688","title":"Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2605.01425","title":"Barriers to Counterfactual Credit Attribution for Autoregressive Models","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.28001","title":"An Empirical Audit of k-NAF Budget Accounting for Anchored Decoding","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.28510","title":"Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2608.27782","title":"Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2610.00251","title":"The Null Is the Hard Part: Exact Tests for Memorization in Generative Models","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.15883","title":"What the Model Cannot See: Covert and Provable Text Invisibility in LLMs","created":"2026-10-11","cited_by_count":0,"area":"safety"}],"next_cursor":null}