{"total":357,"rows":[{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725,"area":"safety"},{"id":"2303.10137","title":"A Recipe for Watermarking Diffusion Models","created":"2023-03-17","cited_by_count":141,"area":"diffusion"},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116,"area":"safety"},{"id":"2310.10669","title":"Unbiased Watermark for Large Language Models","created":"2023-09-22","cited_by_count":111,"area":"safety"},{"id":"2305.04175","title":"Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning","created":"2023-05-07","cited_by_count":92,"area":"diffusion"},{"id":"2302.03162","title":"Protecting Language Generation Models via Invisible Watermarking","created":"2023-02-06","cited_by_count":90,"area":"safety"},{"id":"2106.06361","title":"Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution","created":"2021-06-11","cited_by_count":89,"area":"safety"},{"id":"2210.00875","title":"Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection","created":"2022-09-27","cited_by_count":86,"area":null},{"id":"2103.05633","title":"Proof-of-Learning: Definitions and Practice","created":"2021-03-09","cited_by_count":84,"area":null},{"id":"2112.02701","title":"Protecting Intellectual Property of Language Generation APIs with Lexical Watermark","created":"2021-12-05","cited_by_count":84,"area":"safety"},{"id":"2108.04974","title":"SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)","created":"2021-08-11","cited_by_count":69,"area":null},{"id":"2210.00968","title":"Membership Inference Attacks Against Text-to-image Generation Models","created":"2022-10-03","cited_by_count":69,"area":"safety"},{"id":"2305.10036","title":"Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark","created":"2023-05-17","cited_by_count":67,"area":"safety"},{"id":"2202.08602","title":"Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations","created":"2022-02-17","cited_by_count":61,"area":null},{"id":"2204.06974","title":"Planting Undetectable Backdoors in Machine Learning Models","created":"2022-04-14","cited_by_count":59,"area":null},{"id":"2103.04980","title":"Deep Model Intellectual Property Protection via Deep Watermarking","created":"2021-03-08","cited_by_count":54,"area":"safety"},{"id":"2306.04744","title":"WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models","created":"2023-06-07","cited_by_count":53,"area":"diffusion"},{"id":"2106.06916","title":"Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization","created":"2021-06-13","cited_by_count":52,"area":"safety"},{"id":"2309.16952","title":"Leveraging Optimization for Adaptive Attacks on Image Watermarks","created":"2023-09-29","cited_by_count":52,"area":null},{"id":"2210.07543","title":"Watermarking Pre-trained Language Models with Backdooring","created":"2022-10-14","cited_by_count":50,"area":"safety"},{"id":"2102.04362","title":"Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack","created":"2021-02-08","cited_by_count":46,"area":null},{"id":"2112.03476","title":"Defending against Model Stealing via Verifying Embedded External Features","created":"2021-12-07","cited_by_count":46,"area":null},{"id":"2112.05588","title":"Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models","created":"2021-12-10","cited_by_count":46,"area":"safety"},{"id":"2201.11692","title":"SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders","created":"2022-01-27","cited_by_count":45,"area":null},{"id":"2111.08429","title":"An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences","created":"2021-11-16","cited_by_count":42,"area":null},{"id":"2305.10701","title":"Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models","created":"2023-05-18","cited_by_count":42,"area":"diffusion"},{"id":"2207.07972","title":"Certified Neural Network Watermarks with Randomized Smoothing","created":"2022-07-16","cited_by_count":41,"area":null},{"id":"2209.03466","title":"Supervised GAN Watermarking for Intellectual Property Protection","created":"2022-09-07","cited_by_count":40,"area":null},{"id":"2405.04825","title":"Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution","created":"2024-05-08","cited_by_count":40,"area":"safety"},{"id":"2303.11470","title":"Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarking","created":"2023-03-20","cited_by_count":37,"area":null},{"id":"2304.07361","title":"PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators","created":"2023-04-14","cited_by_count":37,"area":"safety"},{"id":"2305.12502","title":"Watermarking Diffusion Model","created":"2023-05-21","cited_by_count":37,"area":"diffusion"},{"id":"2109.13236","title":"FedIPR: Ownership Verification for Federated Deep Neural Network Models","created":"2021-09-27","cited_by_count":36,"area":"safety"},{"id":"2410.14273","title":"REEF: Representation Encoding Fingerprints for Large Language Models","created":"2024-10-18","cited_by_count":36,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2305.18339","title":"A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutions","created":"2023-05-25","cited_by_count":35,"area":null},{"id":"2308.14401","title":"CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models","created":"2023-08-28","cited_by_count":34,"area":"safety"},{"id":"2312.04828","title":"HuRef: HUman-REadable Fingerprint for Large Language Models","created":"2023-12-08","cited_by_count":34,"area":null},{"id":"2106.08890","title":"ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection","created":"2021-06-11","cited_by_count":33,"area":null},{"id":"2306.04719","title":"Don't trust your eyes: on the (un)reliability of feature visualizations","created":"2023-06-07","cited_by_count":32,"area":null},{"id":"2201.07513","title":"Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders","created":"2022-01-19","cited_by_count":31,"area":null},{"id":"2510.09263","title":"SynthID-Image: Image watermarking at internet scale","created":"2025-10-10","cited_by_count":31,"area":null},{"id":"2210.03312","title":"Distillation-Resistant Watermarking for Model Protection in NLP","created":"2022-10-07","cited_by_count":30,"area":"safety"},{"id":"2211.07160","title":"FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model","created":"2022-11-14","cited_by_count":30,"area":"safety"},{"id":"2108.09187","title":"Quantization Backdoors to Deep Learning Commercial Frameworks","created":"2021-08-20","cited_by_count":29,"area":null},{"id":"2201.11006","title":"An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications","created":"2022-01-26","cited_by_count":29,"area":null},{"id":"2208.11180","title":"Auditing Membership Leakages of Multi-Exit Networks","created":"2022-08-23","cited_by_count":27,"area":null},{"id":"2311.09832","title":"WatME: Towards Lossless Watermarking Through Lexical Redundancy","created":"2023-11-16","cited_by_count":27,"area":null},{"id":"2110.11024","title":"Watermarking Graph Neural Networks based on Backdoor Attacks","created":"2021-10-21","cited_by_count":25,"area":null},{"id":"2109.00685","title":"Excess Capacity and Backdoor Poisoning","created":"2021-09-02","cited_by_count":24,"area":null},{"id":"2505.11541","title":"MorphMark: Flexible Adaptive Watermarking for Large Language Models","created":"2025-05-14","cited_by_count":24,"area":"safety"},{"id":"2201.05889","title":"StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning","created":"2022-01-15","cited_by_count":23,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2201.09243","title":"Increasing the Cost of Model Extraction with Calibrated Proof of Work","created":"2022-01-23","cited_by_count":21,"area":null},{"id":"2206.14157","title":"How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection","created":"2022-06-28","cited_by_count":21,"area":null},{"id":"2208.02820","title":"MOVE: Effective and Harmless Ownership Verification via Embedded External Features","created":"2022-08-04","cited_by_count":21,"area":null},{"id":"2210.15427","title":"Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks","created":"2022-10-21","cited_by_count":21,"area":null},{"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":"2302.09457","title":"Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective","created":"2023-02-19","cited_by_count":20,"area":null},{"id":"2303.09732","title":"Rethinking White-Box Watermarks on Deep Learning Models under Neural Structural Obfuscation","created":"2023-03-17","cited_by_count":20,"area":"safety"},{"id":"2502.12176","title":"Ten Challenging Problems in Federated Foundation Models","created":"2025-02-14","cited_by_count":20,"area":"safety"},{"id":"2508.11548","title":"Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends","created":"2025-08-15","cited_by_count":20,"area":"safety"},{"id":"2306.03436","title":"Intellectual Property Protection of Diffusion Models via the Watermark Diffusion Process","created":"2023-06-06","cited_by_count":19,"area":"diffusion"},{"id":"2404.05188","title":"Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging","created":"2024-04-08","cited_by_count":19,"area":"safety"},{"id":"2111.00162","title":"You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership","created":"2021-10-30","cited_by_count":18,"area":null},{"id":"2204.09975","title":"Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation","created":"2022-04-21","cited_by_count":18,"area":null},{"id":"2405.12725","title":"Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks","created":"2024-05-21","cited_by_count":18,"area":null},{"id":"2104.04268","title":"Reversible Watermarking in Deep Convolutional Neural Networks for Integrity Authentication","created":"2021-04-09","cited_by_count":17,"area":null},{"id":"2202.07183","title":"A Survey of Neural Trojan Attacks and Defenses in Deep Learning","created":"2022-02-15","cited_by_count":17,"area":null},{"id":"2211.07138","title":"Watermarking in Secure Federated Learning: A Verification Framework Based on Client-Side Backdooring","created":"2022-11-14","cited_by_count":17,"area":null},{"id":"2304.06607","title":"False Claims against Model Ownership Resolution","created":"2023-04-13","cited_by_count":17,"area":null},{"id":"2401.15239","title":"MEA-Defender: A Robust Watermark against Model Extraction Attack","created":"2024-01-26","cited_by_count":17,"area":"safety"},{"id":"2106.12478","title":"Teacher Model Fingerprinting Attacks Against Transfer Learning","created":"2021-06-23","cited_by_count":16,"area":null},{"id":"2302.01677","title":"Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks","created":"2023-02-03","cited_by_count":16,"area":null},{"id":"2304.08566","title":"GrOVe: Ownership Verification of Graph Neural Networks using Embeddings","created":"2023-04-17","cited_by_count":16,"area":null},{"id":"2305.00097","title":"NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation","created":"2023-04-28","cited_by_count":16,"area":"safety"},{"id":"2405.02466","title":"ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models","created":"2024-05-03","cited_by_count":16,"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":"2105.14756","title":"A Protection Method of Trained CNN Model with Secret Key from Unauthorized Access","created":"2021-05-31","cited_by_count":15,"area":null},{"id":"2310.11446","title":"Functional Invariants to Watermark Large Transformers","created":"2023-10-17","cited_by_count":15,"area":null},{"id":"2303.11078","title":"Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection","created":"2023-03-20","cited_by_count":14,"area":null},{"id":"2307.10163","title":"Rethinking Backdoor Attacks","created":"2023-07-19","cited_by_count":14,"area":"safety"},{"id":"2406.12844","title":"Synergizing Foundation Models and Federated Learning: A Survey","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2407.10886","title":"SLIP: Securing LLMs IP Using Weights Decomposition","created":"2024-07-15","cited_by_count":14,"area":null},{"id":"2411.11478","title":"SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI","created":"2024-11-18","cited_by_count":14,"area":"safety"},{"id":"2502.07760","title":"Scalable Fingerprinting of Large Language Models","created":"2025-02-11","cited_by_count":14,"area":null},{"id":"2105.13697","title":"AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryption","created":"2021-05-28","cited_by_count":13,"area":"safety"},{"id":"2110.07682","title":"Sound and Complete Neural Network Repair with Minimality and Locality Guarantees","created":"2021-10-14","cited_by_count":13,"area":null},{"id":"2203.02777","title":"Cosine Model Watermarking Against Ensemble Distillation","created":"2022-03-05","cited_by_count":13,"area":"safety"},{"id":"2202.12506","title":"On the Effectiveness of Dataset Watermarking in Adversarial Settings","created":"2022-02-25","cited_by_count":12,"area":null},{"id":"2207.01991","title":"Conflicting Interactions Among Protection Mechanisms for Machine Learning Models","created":"2022-07-05","cited_by_count":12,"area":null},{"id":"2207.05366","title":"Image and Model Transformation with Secret Key for Vision Transformer","created":"2022-07-12","cited_by_count":12,"area":null},{"id":"2211.14952","title":"Federated Learning Attacks and Defenses: A Survey","created":"2022-11-27","cited_by_count":12,"area":null},{"id":"2304.11285","title":"Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks","created":"2023-04-22","cited_by_count":12,"area":"safety"},{"id":"2306.01356","title":"FedCIP: Federated Client Intellectual Property Protection with Traitor Tracking","created":"2023-06-02","cited_by_count":12,"area":"safety"},{"id":"2407.13188","title":"Safe-SD: Safe and Traceable Stable Diffusion with Text Prompt Trigger for Invisible Generative Watermarking","created":"2024-07-18","cited_by_count":12,"area":"diffusion"},{"id":"2509.09703","title":"CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor","created":"2025-09-05","cited_by_count":12,"area":"safety"},{"id":"2201.08217","title":"Watermarking Pre-trained Encoders in Contrastive Learning","created":"2022-01-20","cited_by_count":11,"area":null},{"id":"2307.15539","title":"Beating Backdoor Attack at Its Own Game","created":"2023-07-28","cited_by_count":11,"area":null},{"id":"2311.05863","title":"Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Service","created":"2023-11-10","cited_by_count":11,"area":"mllm"}],"next_cursor":"100"}