{"list":"other","total":53,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"2003.14053","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","created":"2020-03-31","cited_by_count":712},{"id":"1702.07476","title":"Renyi Differential Privacy","created":"2017-02-24","cited_by_count":650},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2007.14321","title":"Label-Only Membership Inference Attacks","created":"2020-07-28","cited_by_count":388},{"id":"2001.02610","title":"iDLG: Improved Deep Leakage from Gradients","created":"2020-01-08","cited_by_count":382},{"id":"1605.02065","title":"Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds","created":"2016-05-06","cited_by_count":346},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258},{"id":"2111.09679","title":"Enhanced Membership Inference Attacks against Machine Learning Models","created":"2021-11-18","cited_by_count":248},{"id":"2011.11660","title":"Differentially Private Learning Needs Better Features (or Much More Data)","created":"2020-11-23","cited_by_count":235},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224},{"id":"2006.07709","title":"Auditing Differentially Private Machine Learning: How Private is Private SGD?","created":"2020-06-13","cited_by_count":218},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195},{"id":"2203.03929","title":"Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks","created":"2022-03-08","cited_by_count":175},{"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},{"id":"2111.08440","title":"On the Importance of Difficulty Calibration in Membership Inference Attacks","created":"2021-11-15","cited_by_count":147},{"id":"1603.01887","title":"Concentrated Differential Privacy","created":"2016-03-06","cited_by_count":144},{"id":"1910.08902","title":"Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations","created":"2019-10-20","cited_by_count":119},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118},{"id":"2110.13057","title":"Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models","created":"2021-10-25","cited_by_count":108},{"id":"1812.00910","title":"Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning","created":"2018-12-03","cited_by_count":77},{"id":"2106.01221","title":"Differential Privacy for Text Analytics via Natural Text Sanitization","created":"2021-06-02","cited_by_count":77},{"id":"2007.09339","title":"ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learning","created":"2020-07-18","cited_by_count":70},{"id":"2205.08514","title":"Recovering Private Text in Federated Learning of Language Models","created":"2022-05-17","cited_by_count":70},{"id":"2103.06819","title":"TAG: Gradient Attack on Transformer-based Language Models","created":"2021-03-11","cited_by_count":63},{"id":"2205.02130","title":"The Limits of Word Level Differential Privacy","created":"2022-05-02","cited_by_count":63},{"id":"2202.08827","title":"LAMP: Extracting Text from Gradients with Language Model Priors","created":"2022-02-17","cited_by_count":54},{"id":"2201.12675","title":"Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models","created":"2022-01-29","cited_by_count":53},{"id":"1811.10256","title":"Generalised Differential Privacy for Text Document Processing","created":"2018-11-26","cited_by_count":52},{"id":"1910.08917","title":"Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text","created":"2019-10-20","cited_by_count":50},{"id":"2009.05886","title":"Differentially Private Language Models Benefit from Public Pre-training","created":"2020-09-13","cited_by_count":47},{"id":"2201.12383","title":"Bounding Training Data Reconstruction in Private (Deep) Learning","created":"2022-01-28","cited_by_count":46},{"id":"2302.07225","title":"Bounding Training Data Reconstruction in DP-SGD","created":"2023-02-14","cited_by_count":46},{"id":"2107.07928","title":"TEM: High Utility Metric Differential Privacy on Text","created":"2021-07-16","cited_by_count":43},{"id":"2206.04055","title":"Gradient Obfuscation Gives a False Sense of Security in Federated Learning","created":"2022-06-08","cited_by_count":39},{"id":"2102.01502","title":"ADePT: Auto-encoder based Differentially Private Text Transformation","created":"2021-01-29","cited_by_count":31},{"id":"2108.04725","title":"PRECODE - A Generic Model Extension to Prevent Deep Gradient Leakage","created":"2021-08-10","cited_by_count":28},{"id":"2302.07636","title":"DP-BART for Privatized Text Rewriting under Local Differential Privacy","created":"2023-02-15","cited_by_count":28},{"id":"2301.09112","title":"Differentially Private Natural Language Models: Recent Advances and Future Directions","created":"2023-01-22","cited_by_count":20},{"id":"2111.00556","title":"Revealing and Protecting Labels in Distributed Training","created":"2021-10-31","cited_by_count":17},{"id":"2402.02987","title":"Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models","created":"2024-02-05","cited_by_count":16},{"id":"2208.08140","title":"Differential Privacy in Natural Language Processing: The Story So Far","created":"2022-08-17","cited_by_count":12},{"id":"2309.16398","title":"Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey","created":"2023-09-28","cited_by_count":12},{"id":"1612.01490","title":"Whiteout: Gaussian Adaptive Noise Regularization in Deep Neural Networks","created":"2016-12-05","cited_by_count":8},{"id":"2210.09375","title":"Reconstruction Attack on Differential Private Trajectory Protection Mechanisms","created":"2022-10-17","cited_by_count":7},{"id":"2205.01258","title":"Universal Optimality and Robust Utility Bounds for Metric Differential Privacy","created":"2022-05-03","cited_by_count":3},{"id":"2406.00999","title":"Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients","created":"2024-06-03","cited_by_count":3},{"id":"2110.08676","title":"Noise-Augmented Privacy-Preserving Empirical Risk Minimization with Dual-purpose Regularizer and Privacy Budget Retrieval and Recycling","created":"2021-10-16","cited_by_count":2}],"next_cursor":null}