{"total":14,"rows":[{"id":"2503.00383","title":"Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems","created":"2025-03-01","cited_by_count":6,"area":null},{"id":"2410.05159","title":"MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2410.05814","title":"Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2411.15702","title":"Editable-DeepSC: Reliable Cross-Modal Semantic Communications for Facial Editing","created":"2024-11-24","cited_by_count":3,"area":null},{"id":"2504.18015","title":"DiffMI: Breaking Face Recognition Privacy via Diffusion-Driven Training-Free Model Inversion","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2409.01062","title":"Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2507.16389","title":"From Flat to Round: Redefining Brain Decoding with Surface-Based fMRI and Cortex Structure","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2604.00955","title":"Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2505.03519","title":"Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2506.09777","title":"Inverting Black-Box Face Recognition Systems via Zero-Order Optimization in Eigenface Space","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2508.20613","title":"Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2607.12354","title":"Reducing information dependency does not cause training data privacy. Adversarially non-robust features do","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.22145","title":"Weak Ties, Strong Signals: Efficient Training Data Detection in Diffusion LLMs via Independent Token Sampling","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2610.07677","title":"Adaptive Model Inversion Attacks Generalize a Privacy-Robustness Tradeoff","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}