{"total":31,"rows":[{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133,"area":null},{"id":"2402.09880","title":"Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence","created":"2024-02-15","cited_by_count":68,"area":null},{"id":"2207.01193","title":"A Customized Text Sanitization Mechanism with Differential Privacy","created":"2022-07-04","cited_by_count":52,"area":null},{"id":"2108.12043","title":"Learning Disentangled Representations in the Imaging Domain","created":"2021-08-26","cited_by_count":46,"area":null},{"id":"2109.06024","title":"Formalizing and Estimating Distribution Inference Risks","created":"2021-09-13","cited_by_count":43,"area":null},{"id":"2206.07284","title":"A Survey on Gradient Inversion: Attacks, Defenses and Future Directions","created":"2022-06-15","cited_by_count":40,"area":null},{"id":"2402.04013","title":"Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses","created":"2024-02-06","cited_by_count":30,"area":null},{"id":"2311.09994","title":"Towards more Practical Threat Models in Artificial Intelligence Security","created":"2023-11-16","cited_by_count":17,"area":null},{"id":"2311.09540","title":"FedFusion: Manifold Driven Federated Learning for Multi-satellite and Multi-modality Fusion","created":"2023-11-16","cited_by_count":8,"area":null},{"id":"2202.08099","title":"Measuring Unintended Memorisation of Unique Private Features in Neural Networks","created":"2022-02-16","cited_by_count":5,"area":null},{"id":"2503.04963","title":"Energy-Latency Attacks: A New Adversarial Threat to Deep Learning","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2505.10496","title":"CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs","created":"2025-05-15","cited_by_count":5,"area":null},{"id":"2211.01656","title":"GRAIMATTER Green Paper: Recommendations for disclosure control of trained Machine Learning (ML) models from Trusted Research Environments (TREs)","created":"2022-11-03","cited_by_count":4,"area":null},{"id":"2206.14541","title":"Why patient data cannot be easily forgotten?","created":"2022-06-29","cited_by_count":3,"area":null},{"id":"2502.15233","title":"A General Pseudonymization Framework for Cloud-Based LLMs: Replacing Privacy Information in Controlled Text Generation","created":"2025-02-21","cited_by_count":3,"area":null},{"id":"2504.16969","title":"Engineering the Law-Machine Learning Translation Problem: Developing Legally Aligned Models","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2411.02099","title":"Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity Recognition","created":"2024-11-04","cited_by_count":2,"area":null},{"id":"2505.02828","title":"Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Review","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2111.05628","title":"Machine Learning Models Disclosure from Trusted Research Environments (TRE), Challenges and Opportunities","created":"2021-11-10","cited_by_count":1,"area":null},{"id":"2201.03004","title":"Privacy-aware Early Detection of COVID-19 through Adversarial Training","created":"2022-01-09","cited_by_count":1,"area":null},{"id":"2205.10079","title":"Unintended memorisation of unique features in neural networks","created":"2022-05-20","cited_by_count":1,"area":null},{"id":"2305.15697","title":"Privacy Protectability: An Information-theoretical Approach","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2504.10190","title":"Differentially Private 2D Human Pose Estimation","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2601.22434","title":"Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2301.07474","title":"Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomy","created":"2023-01-18","cited_by_count":0,"area":null},{"id":"2406.19418","title":"A Quantization-based Technique for Privacy Preserving Distributed Learning","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2409.03707","title":"A Different Level Text Protection Mechanism With Differential Privacy","created":"2024-09-05","cited_by_count":0,"area":null},{"id":"2409.07751","title":"Efficient Privacy-Preserving KAN Inference Using Homomorphic Encryption","created":"2024-09-12","cited_by_count":0,"area":null},{"id":"2411.03746","title":"Optimal Defenses Against Gradient Reconstruction Attacks","created":"2024-11-06","cited_by_count":0,"area":null},{"id":"2411.18746","title":"Inference Privacy: Properties and Mechanisms","created":"2024-11-27","cited_by_count":0,"area":null},{"id":"2602.04927","title":"PriMod4AI: Lifecycle-Aware Privacy Threat Modeling for AI Systems using LLM","created":"2026-02-04","cited_by_count":0,"area":null}],"next_cursor":null}