{"list":"other","total":55,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1511.04599","title":"DeepFool: a simple and accurate method to fool deep neural networks","created":"2015-11-14","cited_by_count":1318},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"1705.07204","title":"Ensemble Adversarial Training: Attacks and Defenses","created":"2017-05-19","cited_by_count":840},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"1511.04508","title":"Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks","created":"2015-11-14","cited_by_count":678},{"id":"1803.06978","title":"Improving Transferability of Adversarial Examples with Input Diversity","created":"2018-03-19","cited_by_count":599},{"id":"1810.11910","title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference","created":"2018-10-29","cited_by_count":521},{"id":"1605.07277","title":"Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples","created":"2016-05-24","cited_by_count":446},{"id":"1804.07998","title":"Generating Natural Language Adversarial Examples","created":"2018-04-21","cited_by_count":424},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"1904.05801","title":"Bridging Theory and Algorithm for Domain Adaptation","created":"2019-04-11","cited_by_count":332},{"id":"1712.02976","title":"Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser","created":"2017-12-08","cited_by_count":329},{"id":"1804.11285","title":"Adversarially Robust Generalization Requires More Data","created":"2018-04-30","cited_by_count":318},{"id":"1906.00695","title":"Continual learning with hypernetworks","created":"2019-06-03","cited_by_count":273},{"id":"2010.06610","title":"Training independent subnetworks for robust prediction","created":"2020-10-13","cited_by_count":177},{"id":"1909.00986","title":"Certified Robustness to Adversarial Word Substitutions","created":"2019-09-03","cited_by_count":168},{"id":"2110.07139","title":"Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer","created":"2021-10-14","cited_by_count":158},{"id":"2008.04859","title":"BREEDS: Benchmarks for Subpopulation Shift","created":"2020-08-11","cited_by_count":155},{"id":"1808.01688","title":"Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models","created":"2018-08-05","cited_by_count":135},{"id":"1906.06032","title":"Adversarial Training Can Hurt Generalization","created":"2019-06-14","cited_by_count":132},{"id":"1906.06919","title":"Improving Black-box Adversarial Attacks with a Transfer-based Prior","created":"2019-06-17","cited_by_count":121},{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119},{"id":"1604.08275","title":"Crafting Adversarial Input Sequences for Recurrent Neural Networks","created":"2016-04-28","cited_by_count":103},{"id":"1905.11736","title":"Cross-Domain Transferability of Adversarial Perturbations","created":"2019-05-28","cited_by_count":92},{"id":"1902.07906","title":"Wasserstein Adversarial Examples via Projected Sinkhorn Iterations","created":"2019-02-21","cited_by_count":89},{"id":"2102.10472","title":"Learning Neural Network Subspaces","created":"2021-02-20","cited_by_count":82},{"id":"1711.10370","title":"Learning to Segment Every Thing","created":"2017-11-28","cited_by_count":65},{"id":"1901.04684","title":"The Limitations of Adversarial Training and the Blind-Spot Attack","created":"2019-01-15","cited_by_count":63},{"id":"1906.06784","title":"Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy","created":"2019-06-16","cited_by_count":49},{"id":"2103.06132","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","created":"2021-03-10","cited_by_count":32},{"id":"1909.06804","title":"Scaling Object Detection by Transferring Classification Weights","created":"2019-09-15","cited_by_count":9},{"id":"2109.01275","title":"A Synergetic Attack against Neural Network Classifiers combining Backdoor and Adversarial Examples","created":"2021-09-03","cited_by_count":6},{"id":"2201.12211","title":"Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire","created":"2022-01-28","cited_by_count":4},{"id":"2203.03692","title":"Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks","created":"2022-03-07","cited_by_count":4}],"next_cursor":null}