{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"1805.12152","title":"Robustness May Be at Odds with Accuracy","created":"2018-05-30","cited_by_count":880},{"id":"1705.07204","title":"Ensemble Adversarial Training: Attacks and Defenses","created":"2017-05-19","cited_by_count":840},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1807.00459","title":"How To Backdoor Federated Learning","created":"2018-07-02","cited_by_count":765},{"id":"1708.06131","title":"Evasion Attacks against Machine Learning at Test Time","created":"2017-08-21","cited_by_count":689},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"1712.09665","title":"Adversarial Patch","created":"2017-12-27","cited_by_count":517},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1811.12470","title":"Analyzing Federated Learning through an Adversarial Lens","created":"2018-11-29","cited_by_count":351},{"id":"2102.01356","title":"Recent Advances in Adversarial Training for Adversarial Robustness","created":"2021-02-02","cited_by_count":279},{"id":"1603.07285","title":"A guide to convolution arithmetic for deep learning","created":"2016-03-23","cited_by_count":185},{"id":"2104.02610","title":"On the Robustness of Vision Transformers to Adversarial Examples","created":"2021-03-31","cited_by_count":167},{"id":"1906.06032","title":"Adversarial Training Can Hurt Generalization","created":"2019-06-14","cited_by_count":132},{"id":"2104.14380","title":"PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments","created":"2021-04-29","cited_by_count":93},{"id":"2205.14141","title":"Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation","created":"2022-05-27","cited_by_count":93},{"id":"2104.06022","title":"Lessons on Parameter Sharing across Layers in Transformers","created":"2021-04-13","cited_by_count":85},{"id":"1901.04684","title":"The Limitations of Adversarial Training and the Blind-Spot Attack","created":"2019-01-15","cited_by_count":63},{"id":"2004.05703","title":"DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments","created":"2020-04-12","cited_by_count":58},{"id":"2110.02797","title":"Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs","created":"2021-10-06","cited_by_count":57},{"id":"1910.07629","title":"A New Defense Against Adversarial Images: Turning a Weakness into a Strength","created":"2019-10-16","cited_by_count":49},{"id":"2203.14046","title":"A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologies","created":"2022-03-26","cited_by_count":44},{"id":"2106.03734","title":"Reveal of Vision Transformers Robustness against Adversarial Attacks","created":"2021-06-07","cited_by_count":43},{"id":"1901.00532","title":"Adversarial Robustness May Be at Odds With Simplicity","created":"2019-01-02","cited_by_count":39},{"id":"1808.00590","title":"MLCapsule: Guarded Offline Deployment of Machine Learning as a Service","created":"2018-08-01","cited_by_count":31},{"id":"2002.04725","title":"More Data Can Expand the Generalization Gap Between Adversarially Robust and Standard Models","created":"2020-02-11","cited_by_count":27},{"id":"2204.09715","title":"Scaling Language Model Size in Cross-Device Federated Learning","created":"2022-03-31","cited_by_count":25},{"id":"2002.07399","title":"Distributed Non-Convex Optimization with Sublinear Speedup under Intermittent Client Availability","created":"2020-02-18","cited_by_count":20},{"id":"2203.02006","title":"Why adversarial training can hurt robust accuracy","created":"2022-03-03","cited_by_count":14},{"id":"2207.03574","title":"Demystifying the Adversarial Robustness of Random Transformation Defenses","created":"2022-06-18","cited_by_count":14},{"id":"1809.00065","title":"MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks","created":"2018-08-31","cited_by_count":8},{"id":"2202.10546","title":"Privacy Leakage of Adversarial Training Models in Federated Learning Systems","created":"2022-02-21","cited_by_count":7},{"id":"2203.04696","title":"Robust Federated Learning Against Adversarial Attacks for Speech Emotion Recognition","created":"2022-03-09","cited_by_count":6},{"id":"2206.08722","title":"WaTZ: A Trusted WebAssembly Runtime Environment with Remote Attestation for TrustZone","created":"2022-06-17","cited_by_count":6},{"id":"1807.00969","title":"Confidential Inference via Ternary Model Partitioning","created":"2018-07-03","cited_by_count":5},{"id":"2208.05895","title":"Shielding Federated Learning Systems against Inference Attacks with ARM TrustZone","created":"2022-08-11","cited_by_count":5}],"next_cursor":null}