{"list":"other","total":54,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"1702.07476","title":"Renyi Differential Privacy","created":"2017-02-24","cited_by_count":650},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"2007.14321","title":"Label-Only Membership Inference Attacks","created":"2020-07-28","cited_by_count":388},{"id":"2109.12298","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","created":"2021-09-25","cited_by_count":383},{"id":"1610.05755","title":"Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data","created":"2016-10-18","cited_by_count":348},{"id":"1702.07464","title":"Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning","created":"2017-02-24","cited_by_count":334},{"id":"1706.09254","title":"The E2E Dataset: New Challenges For End-to-End Generation","created":"2017-06-28","cited_by_count":253},{"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":"1905.03871","title":"Differentially Private Learning with Adaptive Clipping","created":"2019-05-09","cited_by_count":220},{"id":"2106.02848","title":"Numerical Composition of Differential Privacy","created":"2021-06-05","cited_by_count":180},{"id":"2201.04845","title":"Reconstructing Training Data with Informed Adversaries","created":"2022-01-13","cited_by_count":148},{"id":"2007.02871","title":"DART: Open-Domain Structured Data Record to Text Generation","created":"2020-07-06","cited_by_count":145},{"id":"1905.10291","title":"Privacy Risks of Securing Machine Learning Models against Adversarial Examples","created":"2019-05-24","cited_by_count":141},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118},{"id":"2007.03813","title":"Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification","created":"2020-07-07","cited_by_count":90},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88},{"id":"2201.12328","title":"Toward Training at ImageNet Scale with Differential Privacy","created":"2022-01-28","cited_by_count":87},{"id":"2102.12677","title":"Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning","created":"2021-02-25","cited_by_count":86},{"id":"1812.06210","title":"A General Approach to Adding Differential Privacy to Iterative Training Procedures","created":"2018-12-15","cited_by_count":84},{"id":"1908.07643","title":"AdaCliP: Adaptive Clipping for Private SGD","created":"2019-08-20","cited_by_count":77},{"id":"2010.09063","title":"Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization","created":"2020-10-18","cited_by_count":58},{"id":"2203.11481","title":"Mixed Differential Privacy in Computer Vision","created":"2022-03-22","cited_by_count":54},{"id":"2205.10683","title":"Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy","created":"2022-05-21","cited_by_count":48},{"id":"2207.00160","title":"When Does Differentially Private Learning Not Suffer in High Dimensions?","created":"2022-07-01","cited_by_count":48},{"id":"2009.03106","title":"Scaling up Differentially Private Deep Learning with Fast Per-Example Gradient Clipping","created":"2020-09-07","cited_by_count":47},{"id":"2009.05886","title":"Differentially Private Language Models Benefit from Public Pre-training","created":"2020-09-13","cited_by_count":47},{"id":"2106.13756","title":"Private Adaptive Gradient Methods for Convex Optimization","created":"2021-06-25","cited_by_count":46},{"id":"1510.01799","title":"Efficient Per-Example Gradient Computations","created":"2015-10-07","cited_by_count":42},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41},{"id":"2102.03013","title":"Fast and Memory Efficient Differentially Private-SGD via JL Projections","created":"2021-02-05","cited_by_count":29},{"id":"2106.13973","title":"Benchmarking Differential Privacy and Federated Learning for BERT Models","created":"2021-06-26","cited_by_count":28},{"id":"2006.06783","title":"Evading Curse of Dimensionality in Unconstrained Private GLMs via Private Gradient Descent","created":"2020-06-11","cited_by_count":27},{"id":"2107.14586","title":"An Efficient DP-SGD Mechanism for Large Scale NLP Models","created":"2021-07-14","cited_by_count":27},{"id":"1912.11328","title":"Assessing differentially private deep learning with Membership Inference","created":"2019-12-24","cited_by_count":11},{"id":"2206.01836","title":"Dimension Independent Generalization of DP-SGD for Overparameterized Smooth Convex Optimization","created":"2022-06-03","cited_by_count":9}],"next_cursor":null}