{"total":37,"rows":[{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321,"area":"safety"},{"id":"2111.08440","title":"On the Importance of Difficulty Calibration in Membership Inference Attacks","created":"2021-11-15","cited_by_count":147,"area":"safety"},{"id":"2306.01953","title":"Invisible Image Watermarks Are Provably Removable Using Generative AI","created":"2023-06-02","cited_by_count":134,"area":"safety"},{"id":"2102.13179","title":"Machine Unlearning via Algorithmic Stability","created":"2021-02-25","cited_by_count":130,"area":"safety"},{"id":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119,"area":"safety"},{"id":"2309.06746","title":"DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass","created":"2023-09-13","cited_by_count":67,"area":"safety"},{"id":"2210.08911","title":"Forget Unlearning: Towards True Data-Deletion in Machine Learning","created":"2022-10-17","cited_by_count":61,"area":"safety"},{"id":"2104.08305","title":"Membership Inference Attack Susceptibility of Clinical Language Models","created":"2021-04-16","cited_by_count":52,"area":"safety"},{"id":"2401.10371","title":"Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning","created":"2024-01-18","cited_by_count":49,"area":"safety"},{"id":"2302.07225","title":"Bounding Training Data Reconstruction in DP-SGD","created":"2023-02-14","cited_by_count":46,"area":"safety"},{"id":"2304.13169","title":"SAFE: Machine Unlearning With Shard Graphs","created":"2023-04-25","cited_by_count":28,"area":"safety"},{"id":"2204.06106","title":"Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms","created":"2022-04-12","cited_by_count":19,"area":"safety"},{"id":"2410.23232","title":"Attribute-to-Delete: Machine Unlearning via Datamodel Matching","created":"2024-10-30","cited_by_count":18,"area":"safety"},{"id":"2403.17105","title":"Certified Machine Unlearning via Noisy Stochastic Gradient Descent","created":"2024-03-25","cited_by_count":14,"area":"safety"},{"id":"2403.02116","title":"Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks","created":"2024-03-04","cited_by_count":13,"area":"safety"},{"id":"2307.11228","title":"From Adaptive Query Release to Machine Unlearning","created":"2023-07-20","cited_by_count":10,"area":"safety"},{"id":"2311.14056","title":"DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release","created":"2023-11-23","cited_by_count":10,"area":"safety"},{"id":"2102.03314","title":"On Utility and Privacy in Synthetic Genomic Data","created":"2021-02-05","cited_by_count":8,"area":"safety"},{"id":"2507.04531","title":"DP-Fusion: Token-Level Differentially Private Inference for Large Language Models","created":"2025-07-06","cited_by_count":6,"area":"safety"},{"id":"2103.02895","title":"On the privacy-utility trade-off in differentially private hierarchical text classification","created":"2021-03-04","cited_by_count":4,"area":"safety"},{"id":"2211.06582","title":"Provable Membership Inference Privacy","created":"2022-11-12","cited_by_count":4,"area":"safety"},{"id":"2601.22359","title":"The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples","created":"2026-01-29","cited_by_count":4,"area":"safety"},{"id":"2204.07877","title":"Assessing Differentially Private Variational Autoencoders under Membership Inference","created":"2022-04-16","cited_by_count":2,"area":"safety"},{"id":"2408.01040","title":"Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMix","created":"2024-08-02","cited_by_count":2,"area":"safety"},{"id":"2410.09947","title":"Efficient Federated Unlearning under Plausible Deniability","created":"2024-10-13","cited_by_count":2,"area":"safety"},{"id":"2507.08158","title":"A Unified Framework for Adversary-Aware Differential Privacy Bounds","created":"2025-07-10","cited_by_count":2,"area":"safety"},{"id":"2409.13004","title":"Data Poisoning and Leakage Analysis in Federated Learning","created":"2024-09-19","cited_by_count":1,"area":"safety"},{"id":"2504.16683","title":"MCMC for Bayesian estimation of Differential Privacy from Membership Inference Attacks","created":"2025-04-23","cited_by_count":1,"area":"safety"},{"id":"2505.08557","title":"Online Learning and Unlearning","created":"2025-05-13","cited_by_count":1,"area":"safety"},{"id":"2410.07414","title":"Bayes-Nash Generative Privacy Against Membership Inference Attacks","created":"2024-10-09","cited_by_count":0,"area":"safety"},{"id":"2601.05134","title":"Sequential Subspace Noise Injection Prevents Accuracy Collapse in Certified Unlearning","created":"2026-01-08","cited_by_count":0,"area":"safety"},{"id":"2601.10045","title":"Privacy Enhanced PEFT: Tensor Train Decomposition Improves Privacy Utility Tradeoffs under DP-SGD","created":"2026-01-15","cited_by_count":0,"area":"safety"},{"id":"2602.15602","title":"Certified Per-Instance Unlearning Using Individual Sensitivity Bounds","created":"2026-02-17","cited_by_count":0,"area":"safety"},{"id":"2602.23798","title":"MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models","created":"2026-02-27","cited_by_count":0,"area":"safety"},{"id":"2604.21571","title":"Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies","created":"2026-04-23","cited_by_count":0,"area":"safety"},{"id":"2605.11170","title":"Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data","created":"2026-05-11","cited_by_count":0,"area":"safety"},{"id":"2605.27292","title":"Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run","created":"2026-05-26","cited_by_count":0,"area":"safety"}],"next_cursor":null}