{"total":148,"rows":[{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732,"area":"diffusion"},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224,"area":null},{"id":"2303.00654","title":"How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy","created":"2023-03-01","cited_by_count":153,"area":null},{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133,"area":null},{"id":"2210.17546","title":"Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy","created":"2022-10-31","cited_by_count":100,"area":null},{"id":"2403.01218","title":"Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy","created":"2024-03-02","cited_by_count":82,"area":"safety"},{"id":"2402.01822","title":"Building Guardrails for Large Language Models","created":"2024-02-02","cited_by_count":65,"area":"safety"},{"id":"2212.01539","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","created":"2022-12-03","cited_by_count":52,"area":null},{"id":"2212.10986","title":"SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning","created":"2022-12-21","cited_by_count":51,"area":null},{"id":"2201.12383","title":"Bounding Training Data Reconstruction in Private (Deep) Learning","created":"2022-01-28","cited_by_count":46,"area":null},{"id":"2302.07225","title":"Bounding Training Data Reconstruction in DP-SGD","created":"2023-02-14","cited_by_count":46,"area":"safety"},{"id":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45,"area":null},{"id":"2409.19732","title":"Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement","created":"2024-09-29","cited_by_count":45,"area":"safety"},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2309.05610","title":"Privacy Side Channels in Machine Learning Systems","created":"2023-09-11","cited_by_count":40,"area":null},{"id":"2302.03098","title":"One-shot Empirical Privacy Estimation for Federated Learning","created":"2023-02-06","cited_by_count":36,"area":null},{"id":"2208.12348","title":"SNAP: Efficient Extraction of Private Properties with Poisoning","created":"2022-08-25","cited_by_count":31,"area":null},{"id":"2410.22235","title":"Auditing $f$-Differential Privacy in One Run","created":"2024-10-29","cited_by_count":30,"area":null},{"id":"2312.14334","title":"DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction)","created":"2023-12-21","cited_by_count":28,"area":null},{"id":"2307.01827","title":"Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses","created":"2023-07-04","cited_by_count":26,"area":null},{"id":"2405.20272","title":"Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable","created":"2024-05-30","cited_by_count":25,"area":"safety"},{"id":"2210.02912","title":"CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning","created":"2022-10-06","cited_by_count":24,"area":null},{"id":"2305.02279","title":"Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models","created":"2023-05-03","cited_by_count":24,"area":null},{"id":"2309.17310","title":"Leave-one-out Distinguishability in Machine Learning","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2304.13850","title":"Do SSL Models Have D\\'ej\\`a Vu? A Case of Unintended Memorization in Self-supervised Learning","created":"2023-04-26","cited_by_count":19,"area":null},{"id":"2306.06076","title":"Differentially Private Image Classification by Learning Priors from Random Processes","created":"2023-06-08","cited_by_count":19,"area":null},{"id":"2405.14457","title":"Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model","created":"2024-05-23","cited_by_count":18,"area":null},{"id":"2210.13662","title":"Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano","created":"2022-10-24","cited_by_count":17,"area":null},{"id":"2302.01622","title":"Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging","created":"2023-02-03","cited_by_count":17,"area":null},{"id":"2308.10888","title":"Unlocking Accuracy and Fairness in Differentially Private Image Classification","created":"2023-08-21","cited_by_count":16,"area":null},{"id":"2307.03928","title":"Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy","created":"2023-07-08","cited_by_count":15,"area":null},{"id":"2507.06969","title":"Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy","created":"2025-07-09","cited_by_count":15,"area":null},{"id":"2312.05114","title":"The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against \"Truly Anonymous\" Synthetic Datasets","created":"2023-12-08","cited_by_count":14,"area":null},{"id":"2411.10242","title":"Measuring Non-Adversarial Reproduction of Training Data in Large Language Models","created":"2024-11-15","cited_by_count":14,"area":null},{"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":"2412.05734","title":"LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage","created":"2024-12-07","cited_by_count":13,"area":"agents"},{"id":"2302.01190","title":"On the Efficacy of Differentially Private Few-shot Image Classification","created":"2023-02-02","cited_by_count":12,"area":null},{"id":"2306.03235","title":"Information Flow Control in Machine Learning through Modular Model Architecture","created":"2023-06-05","cited_by_count":11,"area":null},{"id":"2310.20579","title":"Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks","created":"2023-10-31","cited_by_count":10,"area":null},{"id":"2306.05093","title":"Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2406.08918","title":"Beyond the Calibration Point: Mechanism Comparison in Differential Privacy","created":"2024-06-13","cited_by_count":9,"area":null},{"id":"2407.02191","title":"Attack-Aware Noise Calibration for Differential Privacy","created":"2024-07-02","cited_by_count":8,"area":null},{"id":"2203.00481","title":"Beyond Gradients: Exploiting Adversarial Priors in Model Inversion Attacks","created":"2022-03-01","cited_by_count":7,"area":null},{"id":"2204.08345","title":"Extracting Targeted Training Data from ASR Models, and How to Mitigate It","created":"2022-04-18","cited_by_count":7,"area":null},{"id":"2211.13403","title":"Differentially Private Image Classification from Features","created":"2022-11-24","cited_by_count":7,"area":null},{"id":"2305.03350","title":"Reconstructing Training Data from Multiclass Neural Networks","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2402.06674","title":"Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning","created":"2024-02-07","cited_by_count":7,"area":"safety"},{"id":"2403.02571","title":"DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2411.05743","title":"Free Record-Level Privacy Risk Evaluation Through Artifact-Based Methods","created":"2024-11-08","cited_by_count":7,"area":"safety"},{"id":"2211.03942","title":"Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design","created":"2022-11-08","cited_by_count":6,"area":null},{"id":"2211.05249","title":"QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based Systems","created":"2022-11-09","cited_by_count":6,"area":null},{"id":"2306.00133","title":"A Note On Interpreting Canary Exposure","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2306.06503","title":"Preserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacy","created":"2023-06-10","cited_by_count":6,"area":null},{"id":"2306.13789","title":"Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models","created":"2023-06-23","cited_by_count":6,"area":null},{"id":"2409.08482","title":"Risks When Sharing LoRA Fine-Tuned Diffusion Model Weights","created":"2024-09-13","cited_by_count":6,"area":"diffusion"},{"id":"2409.18214","title":"Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey","created":"2024-09-26","cited_by_count":6,"area":"diffusion"},{"id":"2502.19770","title":"TAPE: Tailored Posterior Difference for Auditing of Machine Unlearning","created":"2025-02-27","cited_by_count":6,"area":"safety"},{"id":"2503.07501","title":"Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2310.03838","title":"Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning","created":"2023-10-05","cited_by_count":5,"area":"safety"},{"id":"2310.11739","title":"Unintended Memorization in Large ASR Models, and How to Mitigate It","created":"2023-10-18","cited_by_count":5,"area":null},{"id":"2403.02506","title":"Differentially Private Representation Learning via Image Captioning","created":"2024-03-04","cited_by_count":5,"area":null},{"id":"2404.16847","title":"State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Survey","created":"2024-02-25","cited_by_count":5,"area":null},{"id":"2409.16593","title":"A Hybrid Quantum Neural Network for Split Learning","created":"2024-09-25","cited_by_count":5,"area":null},{"id":"2506.07888","title":"SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmark","created":"2025-06-09","cited_by_count":5,"area":null},{"id":"2509.07055","title":"Sequentially Auditing Differential Privacy","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2206.14439","title":"Approximate Data Deletion in Generative Models","created":"2022-06-29","cited_by_count":4,"area":null},{"id":"2301.13104","title":"Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models","created":"2023-01-30","cited_by_count":4,"area":null},{"id":"2403.01268","title":"Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach","created":"2024-03-02","cited_by_count":4,"area":null},{"id":"2408.16913","title":"Analyzing Inference Privacy Risks Through Gradients in Machine Learning","created":"2024-08-29","cited_by_count":4,"area":null},{"id":"2409.12367","title":"Extracting Memorized Training Data via Decomposition","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2409.19078","title":"Differential privacy enables fair and accurate AI-based analysis of speech disorders while protecting patient data","created":"2024-09-27","cited_by_count":4,"area":null},{"id":"2412.08544","title":"Training Data Reconstruction: Privacy due to Uncertainty?","created":"2024-12-11","cited_by_count":4,"area":null},{"id":"2412.20269","title":"TeLU Activation Function for Fast and Stable Deep Learning","created":"2024-12-28","cited_by_count":4,"area":null},{"id":"2506.15553","title":"Approximating Language Model Training Data from Weights","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2510.13451","title":"Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts","created":"2025-10-15","cited_by_count":4,"area":"safety"},{"id":"2201.06093","title":"Adversarial Machine Learning Threat Analysis and Remediation in Open Radio Access Network (O-RAN)","created":"2022-01-16","cited_by_count":3,"area":null},{"id":"2406.17298","title":"Efficient and Scalable Implementation of Differentially Private Deep Learning without Shortcuts","created":"2024-06-25","cited_by_count":3,"area":null},{"id":"2407.12669","title":"Enhancing the Utility of Privacy-Preserving Cancer Classification using Synthetic Data","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2412.21123","title":"ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation","created":"2024-12-30","cited_by_count":3,"area":"safety"},{"id":"2503.00592","title":"SolidMark: Evaluating Image Memorization in Generative Models","created":"2025-03-01","cited_by_count":3,"area":"diffusion"},{"id":"2503.12314","title":"Empirical Privacy Variance","created":"2025-03-16","cited_by_count":3,"area":null},{"id":"2509.22214","title":"A Law of Data Reconstruction for Random Features (and Beyond)","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2511.06305","title":"Setting $\\varepsilon$ is not the Issue in Differential Privacy","created":"2025-11-09","cited_by_count":3,"area":null},{"id":"2511.07843","title":"DP-AdamW: Investigating Decoupled Weight Decay and Bias Correction in Private Deep Learning","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2601.18650","title":"FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning","created":"2026-01-26","cited_by_count":3,"area":"safety"},{"id":"2211.10173","title":"How Do Input Attributes Impact the Privacy Loss in Differential Privacy?","created":"2022-11-18","cited_by_count":2,"area":null},{"id":"2402.07334","title":"Differentially Private Training of Mixture of Experts Models","created":"2024-02-11","cited_by_count":2,"area":"moe"},{"id":"2402.08344","title":"Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2403.07588","title":"Visual Privacy Auditing with Diffusion Models","created":"2024-03-12","cited_by_count":2,"area":"diffusion"},{"id":"2406.02797","title":"Auditing Privacy Mechanisms via Label Inference Attacks","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2505.15738","title":"Checkpoint-GCG: Auditing and Attacking Fine-Tuning-Based Prompt Injection Defenses","created":"2025-05-21","cited_by_count":2,"area":"agents"},{"id":"2506.22506","title":"SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning","created":"2025-06-25","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":"2512.09953","title":"ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofs","created":"2025-12-09","cited_by_count":2,"area":"safety"},{"id":"2601.19618","title":"The pretraining domain outweighs the training objective in setting the privacy-utility trade-off of differentially private medical image analysis","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2603.12142","title":"Understanding Disclosure Risk in Differential Privacy with Applications to Noise Calibration and Auditing (Extended Version)","created":"2026-03-12","cited_by_count":2,"area":"safety"},{"id":"2210.04840","title":"Rieoptax: Riemannian Optimization in JAX","created":"2022-10-10","cited_by_count":1,"area":null},{"id":"2301.07557","title":"Targeted Image Reconstruction by Sampling Pre-trained Diffusion Model","created":"2023-01-18","cited_by_count":1,"area":"diffusion"},{"id":"2306.04109","title":"Membership inference attack with relative decision boundary distance","created":"2023-06-07","cited_by_count":1,"area":"safety"},{"id":"2306.13892","title":"Generalizing Differentially Private Decentralized Deep Learning with Multi-Agent Consensus","created":"2023-06-24","cited_by_count":1,"area":null}],"next_cursor":"100"}