{"list":"other","total":192,"rows":[{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1705.07204","title":"Ensemble Adversarial Training: Attacks and Defenses","created":"2017-05-19","cited_by_count":840},{"id":"1807.00459","title":"How To Backdoor Federated Learning","created":"2018-07-02","cited_by_count":765},{"id":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"id":"1805.12185","title":"Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks","created":"2018-05-30","cited_by_count":580},{"id":"1711.00117","title":"Countering Adversarial Images using Input Transformations","created":"2017-10-31","cited_by_count":520},{"id":"2002.11569","title":"Overfitting in adversarially robust deep learning","created":"2020-02-26","cited_by_count":506},{"id":"1704.01155","title":"Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks","created":"2017-04-04","cited_by_count":486},{"id":"1811.00636","title":"Spectral Signatures in Backdoor Attacks","created":"2018-11-01","cited_by_count":484},{"id":"2205.07460","title":"Diffusion Models for Adversarial Purification","created":"2022-05-16","cited_by_count":476},{"id":"1902.06531","title":"STRIP: A Defence Against Trojan Attacks on Deep Neural Networks","created":"2019-02-18","cited_by_count":459},{"id":"1811.03728","title":"Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering","created":"2018-11-09","cited_by_count":456},{"id":"1905.13736","title":"Unlabeled Data Improves Adversarial Robustness","created":"2019-05-31","cited_by_count":416},{"id":"1805.06605","title":"Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models","created":"2018-05-17","cited_by_count":362},{"id":"1712.02976","title":"Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser","created":"2017-12-08","cited_by_count":329},{"id":"2101.05930","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","created":"2021-01-15","cited_by_count":324},{"id":"2007.05084","title":"Attack of the Tails: Yes, You Really Can Backdoor Federated Learning","created":"2020-07-09","cited_by_count":309},{"id":"1801.02613","title":"Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality","created":"2018-01-08","cited_by_count":282},{"id":"2006.04152","title":"BERT Loses Patience: Fast and Robust Inference with Early Exit","created":"2020-06-07","cited_by_count":273},{"id":"1705.09064","title":"MagNet: a Two-Pronged Defense against Adversarial Examples","created":"2017-05-25","cited_by_count":269},{"id":"2110.11571","title":"Anti-Backdoor Learning: Training Clean Models on Poisoned Data","created":"2021-10-22","cited_by_count":263},{"id":"1911.07963","title":"Can You Really Backdoor Federated Learning?","created":"2019-11-18","cited_by_count":255},{"id":"1703.00410","title":"Detecting Adversarial Samples from Artifacts","created":"2017-03-01","cited_by_count":245},{"id":"1710.10766","title":"PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples","created":"2017-10-30","cited_by_count":244},{"id":"2002.11242","title":"Attacks Which Do Not Kill Training Make Adversarial Learning Stronger","created":"2020-02-26","cited_by_count":243},{"id":"2110.14430","title":"Adversarial Neuron Pruning Purifies Backdoored Deep Models","created":"2021-10-27","cited_by_count":235},{"id":"2110.09468","title":"Improving Robustness using Generated Data","created":"2021-10-18","cited_by_count":234},{"id":"1702.04267","title":"On Detecting Adversarial Perturbations","created":"2017-02-14","cited_by_count":232},{"id":"1803.04765","title":"Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning","created":"2018-03-13","cited_by_count":207},{"id":"1910.03137","title":"Detecting AI Trojans Using Meta Neural Analysis","created":"2019-10-08","cited_by_count":199},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187},{"id":"1904.13000","title":"Adversarial Training and Robustness for Multiple Perturbations","created":"2019-04-30","cited_by_count":183},{"id":"1905.00877","title":"You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle","created":"2019-05-02","cited_by_count":183},{"id":"1702.06280","title":"On the (Statistical) Detection of Adversarial Examples","created":"2017-02-21","cited_by_count":180},{"id":"2006.04924","title":"A Self-supervised Approach for Adversarial Robustness","created":"2020-06-08","cited_by_count":180},{"id":"2012.10544","title":"Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses","created":"2020-12-18","cited_by_count":180},{"id":"2002.05990","title":"Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets","created":"2020-02-14","cited_by_count":167},{"id":"2110.03735","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","created":"2021-10-07","cited_by_count":166},{"id":"1805.02628","title":"PRADA: Protecting against DNN Model Stealing Attacks","created":"2018-05-07","cited_by_count":165},{"id":"1905.13725","title":"Are Labels Required for Improving Adversarial Robustness?","created":"2019-05-31","cited_by_count":163},{"id":"1808.04866","title":"Mitigating Sybils in Federated Learning Poisoning","created":"2018-08-14","cited_by_count":161},{"id":"2104.03413","title":"Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective","created":"2021-04-07","cited_by_count":161},{"id":"2202.03423","title":"Backdoor Defense via Decoupling the Training Process","created":"2022-02-05","cited_by_count":153},{"id":"1812.00292","title":"SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems","created":"2018-12-02","cited_by_count":152},{"id":"1906.10842","title":"Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs","created":"2019-06-26","cited_by_count":146},{"id":"2106.06041","title":"Adversarial purification with Score-based generative models","created":"2021-06-11","cited_by_count":134},{"id":"2005.00060","title":"Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness","created":"2020-04-30","cited_by_count":132},{"id":"2112.08304","title":"On the Convergence and Robustness of Adversarial Training","created":"2021-12-15","cited_by_count":130},{"id":"1908.00686","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","created":"2019-08-02","cited_by_count":124},{"id":"2007.10760","title":"Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review","created":"2020-07-21","cited_by_count":123},{"id":"2003.08904","title":"RAB: Provable Robustness Against Backdoor Attacks","created":"2020-03-19","cited_by_count":118},{"id":"2311.12075","title":"BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning","created":"2023-11-20","cited_by_count":115},{"id":"2202.10103","title":"Robustness and Accuracy Could Be Reconcilable by (Proper) Definition","created":"2022-02-21","cited_by_count":111},{"id":"2103.15670","title":"On the Adversarial Robustness of Vision Transformers","created":"2021-03-29","cited_by_count":106},{"id":"1811.12673","title":"ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples","created":"2018-11-30","cited_by_count":105},{"id":"1803.05787","title":"Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples","created":"2018-03-14","cited_by_count":99},{"id":"2102.05123","title":"Backdoor Scanning for Deep Neural Networks through K-Arm Optimization","created":"2021-02-09","cited_by_count":98},{"id":"2302.03251","title":"SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency","created":"2023-02-07","cited_by_count":97},{"id":"1911.07116","title":"Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy","created":"2019-11-16","cited_by_count":95},{"id":"2007.15802","title":"Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases","created":"2020-07-31","cited_by_count":95},{"id":"2203.06616","title":"LAS-AT: Adversarial Training with Learnable Attack Strategy","created":"2022-03-13","cited_by_count":95},{"id":"1805.04807","title":"Curriculum Adversarial Training","created":"2018-05-13","cited_by_count":89},{"id":"2006.14536","title":"Smooth Adversarial Training","created":"2020-06-25","cited_by_count":89},{"id":"1909.04068","title":"Adversarial Robustness Against the Union of Multiple Perturbation Models","created":"2019-09-09","cited_by_count":88},{"id":"2002.00211","title":"Learning to Detect Malicious Clients for Robust Federated Learning","created":"2020-02-01","cited_by_count":88},{"id":"1705.02900","title":"Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression","created":"2017-05-08","cited_by_count":87},{"id":"1911.10695","title":"When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks","created":"2019-11-25","cited_by_count":87},{"id":"1910.04749","title":"Defending Neural Backdoors via Generative Distribution Modeling","created":"2019-10-10","cited_by_count":84},{"id":"2007.03767","title":"Defending against Backdoors in Federated Learning with Robust Learning Rate","created":"2020-07-07","cited_by_count":82},{"id":"2002.05999","title":"Adversarial Distributional Training for Robust Deep Learning","created":"2020-02-14","cited_by_count":79},{"id":"2010.01279","title":"Do Wider Neural Networks Really Help Adversarial Robustness?","created":"2020-10-03","cited_by_count":79},{"id":"2109.05211","title":"RobustART: Benchmarking Robustness on Architecture Design and Training Techniques","created":"2021-09-11","cited_by_count":79},{"id":"2208.03111","title":"Data-free Backdoor Removal based on Channel Lipschitzness","created":"2022-08-05","cited_by_count":79},{"id":"1612.07767","title":"Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics","created":"2016-12-22","cited_by_count":77},{"id":"1704.00103","title":"SafetyNet: Detecting and Rejecting Adversarial Examples Robustly","created":"2017-04-01","cited_by_count":76},{"id":"2010.01799","title":"Understanding Catastrophic Overfitting in Single-step Adversarial Training","created":"2020-10-05","cited_by_count":76},{"id":"2110.03825","title":"Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks","created":"2021-10-07","cited_by_count":74},{"id":"2003.02484","title":"Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalization","created":"2020-03-05","cited_by_count":73},{"id":"2009.14720","title":"DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles","created":"2020-09-30","cited_by_count":73},{"id":"2103.13127","title":"Black-box Detection of Backdoor Attacks with Limited Information and Data","created":"2021-03-24","cited_by_count":73},{"id":"1909.06872","title":"Detecting Adversarial Samples Using Influence Functions and Nearest Neighbors","created":"2019-09-15","cited_by_count":72},{"id":"2305.10036","title":"Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark","created":"2023-05-17","cited_by_count":67},{"id":"2105.11144","title":"Improved OOD Generalization via Adversarial Training and Pre-training","created":"2021-05-24","cited_by_count":66},{"id":"1901.01677","title":"Image Super-Resolution as a Defense Against Adversarial Attacks","created":"2019-01-07","cited_by_count":65},{"id":"2304.11823","title":"Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization","created":"2023-04-24","cited_by_count":64},{"id":"2209.11715","title":"The \"Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices","created":"2022-09-23","cited_by_count":63},{"id":"2303.03323","title":"CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning","created":"2023-03-06","cited_by_count":63},{"id":"2012.03765","title":"Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks","created":"2020-12-07","cited_by_count":60},{"id":"1906.07916","title":"Convergence of Adversarial Training in Overparametrized Neural Networks","created":"2019-06-19","cited_by_count":58},{"id":"2005.13525","title":"Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models","created":"2020-05-27","cited_by_count":58},{"id":"1707.05474","title":"APE-GAN: Adversarial Perturbation Elimination with GAN","created":"2017-07-18","cited_by_count":57},{"id":"2106.07904","title":"Probabilistic Margins for Instance Reweighting in Adversarial Training","created":"2021-06-15","cited_by_count":57},{"id":"2310.14942","title":"Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand","created":"2023-10-09","cited_by_count":57},{"id":"1907.05587","title":"Stateful Detection of Black-Box Adversarial Attacks","created":"2019-07-12","cited_by_count":56},{"id":"2303.15180","title":"Detecting Backdoors in Pre-trained Encoders","created":"2023-03-23","cited_by_count":55},{"id":"2110.14880","title":"AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis","created":"2021-10-28","cited_by_count":53}],"next_cursor":"100"}