{"list":"other","total":173,"rows":[{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"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":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"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":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1805.12152","title":"Robustness May Be at Odds with Accuracy","created":"2018-05-30","cited_by_count":880},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"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":"1801.07593","title":"Mitigating Unwanted Biases with Adversarial Learning","created":"2018-01-22","cited_by_count":663},{"id":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"1609.02943","title":"Stealing Machine Learning Models via Prediction APIs","created":"2016-09-09","cited_by_count":619},{"id":"1803.02453","title":"A Reductions Approach to Fair Classification","created":"2018-03-06","cited_by_count":587},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"id":"1805.04049","title":"Exploiting Unintended Feature Leakage in Collaborative Learning","created":"2018-05-10","cited_by_count":520},{"id":"1804.00792","title":"Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks","created":"2018-04-03","cited_by_count":519},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"1802.03471","title":"Certified Robustness to Adversarial Examples with Differential Privacy","created":"2018-02-09","cited_by_count":468},{"id":"1906.05271","title":"Does Learning Require Memorization? A Short Tale about a Long Tail","created":"2019-06-12","cited_by_count":460},{"id":"1709.02012","title":"On Fairness and Calibration","created":"2017-09-06","cited_by_count":406},{"id":"2007.14321","title":"Label-Only Membership Inference Attacks","created":"2020-07-28","cited_by_count":388},{"id":"1802.04633","title":"Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring","created":"2018-02-13","cited_by_count":357},{"id":"1904.02144","title":"HopSkipJumpAttack: A Query-Efficient Decision-Based Attack","created":"2019-04-03","cited_by_count":333},{"id":"1802.07927","title":"The Hidden Vulnerability of Distributed Learning in Byzantium","created":"2018-02-22","cited_by_count":329},{"id":"2104.07586","title":"See through Gradients: Image Batch Recovery via GradInversion","created":"2021-04-15","cited_by_count":326},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321},{"id":"1905.12101","title":"Differential Privacy Has Disparate Impact on Model Accuracy","created":"2019-05-28","cited_by_count":316},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314},{"id":"1812.02766","title":"Knockoff Nets: Stealing Functionality of Black-Box Models","created":"2018-12-06","cited_by_count":292},{"id":"1902.10275","title":"Towards Efficient Data Valuation Based on the Shapley Value","created":"2019-02-27","cited_by_count":281},{"id":"2111.09679","title":"Enhanced Membership Inference Attacks against Machine Learning Models","created":"2021-11-18","cited_by_count":248},{"id":"1911.07135","title":"The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks","created":"2019-11-17","cited_by_count":246},{"id":"2006.07500","title":"Domain Generalization using Causal Matching","created":"2020-06-12","cited_by_count":225},{"id":"1906.07983","title":"Explanations can be manipulated and geometry is to blame","created":"2019-06-19","cited_by_count":216},{"id":"1702.06280","title":"On the (Statistical) Detection of Adversarial Examples","created":"2017-02-21","cited_by_count":180},{"id":"1811.09716","title":"Robustness via curvature regularization, and vice versa","created":"2018-11-23","cited_by_count":175},{"id":"1709.07886","title":"Machine Learning Models that Remember Too Much","created":"2017-09-22","cited_by_count":169},{"id":"1805.02628","title":"PRADA: Protecting against DNN Model Stealing Attacks","created":"2018-05-07","cited_by_count":165},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156},{"id":"2002.10716","title":"Understanding and Mitigating the Tradeoff Between Robustness and Accuracy","created":"2020-02-25","cited_by_count":149},{"id":"1908.08619","title":"Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms","created":"2019-08-22","cited_by_count":148},{"id":"1705.10378","title":"Fair Inference On Outcomes","created":"2017-05-29","cited_by_count":144},{"id":"1905.10291","title":"Privacy Risks of Securing Machine Learning Models against Adversarial Examples","created":"2019-05-24","cited_by_count":141},{"id":"1910.12366","title":"Thieves on Sesame Street! Model Extraction of BERT-based APIs","created":"2019-10-27","cited_by_count":139},{"id":"2010.06121","title":"To be Robust or to be Fair: Towards Fairness in Adversarial Training","created":"2020-10-13","cited_by_count":137},{"id":"2206.10469","title":"The Privacy Onion Effect: Memorization is Relative","created":"2022-06-21","cited_by_count":136},{"id":"1306.4447","title":"Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifiers","created":"2013-06-19","cited_by_count":130},{"id":"2003.08904","title":"RAB: Provable Robustness Against Backdoor Attacks","created":"2020-03-19","cited_by_count":118},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116},{"id":"2106.02666","title":"Counterfactual Explanations Can Be Manipulated","created":"2021-06-04","cited_by_count":113},{"id":"1902.02041","title":"Fooling Neural Network Interpretations via Adversarial Model Manipulation","created":"2019-02-06","cited_by_count":112},{"id":"2002.11328","title":"Rethinking Bias-Variance Trade-off for Generalization of Neural Networks","created":"2020-02-26","cited_by_count":107},{"id":"2009.04131","title":"SoK: Certified Robustness for Deep Neural Networks","created":"2020-09-09","cited_by_count":105},{"id":"2012.06421","title":"When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?","created":"2020-12-11","cited_by_count":104},{"id":"2204.00032","title":"Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets","created":"2022-03-31","cited_by_count":101},{"id":"1906.00830","title":"DAWN: Dynamic Adversarial Watermarking of Neural Networks","created":"2019-06-03","cited_by_count":100},{"id":"1912.00888","title":"Deep Neural Network Fingerprinting by Conferrable Adversarial Examples","created":"2019-12-02","cited_by_count":93},{"id":"2106.08283","title":"CRFL: Certifiably Robust Federated Learning against Backdoor Attacks","created":"2021-06-15","cited_by_count":91},{"id":"2011.09527","title":"Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff","created":"2020-11-18","cited_by_count":89},{"id":"2210.00875","title":"Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection","created":"2022-09-27","cited_by_count":86},{"id":"2102.02551","title":"ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models","created":"2021-02-04","cited_by_count":85},{"id":"2002.11497","title":"On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping","created":"2020-02-26","cited_by_count":83},{"id":"2011.03731","title":"On the Privacy Risks of Algorithmic Fairness","created":"2020-11-07","cited_by_count":82},{"id":"1903.09860","title":"Data Poisoning against Differentially-Private Learners: Attacks and Defenses","created":"2019-03-23","cited_by_count":78},{"id":"1812.02696","title":"Differentially Private Fair Learning","created":"2018-12-06","cited_by_count":76},{"id":"1905.11742","title":"Overlearning Reveals Sensitive Attributes","created":"2019-05-28","cited_by_count":76},{"id":"1812.00891","title":"Interpretable Deep Learning under Fire","created":"2018-12-03","cited_by_count":74},{"id":"2202.00580","title":"Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification","created":"2022-02-01","cited_by_count":73},{"id":"1806.05476","title":"Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data","created":"2018-06-14","cited_by_count":70},{"id":"2006.14026","title":"Subpopulation Data Poisoning Attacks","created":"2020-06-24","cited_by_count":70},{"id":"2108.04974","title":"SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)","created":"2021-08-11","cited_by_count":69},{"id":"2002.00937","title":"Radioactive data: tracing through training","created":"2020-02-03","cited_by_count":67},{"id":"2108.06504","title":"LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis","created":"2021-08-14","cited_by_count":65},{"id":"2202.08602","title":"Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations","created":"2022-02-17","cited_by_count":61},{"id":"2101.11073","title":"Property Inference From Poisoning","created":"2021-01-26","cited_by_count":60},{"id":"2106.03216","title":"On Memorization in Probabilistic Deep Generative Models","created":"2021-06-06","cited_by_count":60},{"id":"2004.07401","title":"Poisoning Attacks on Algorithmic Fairness","created":"2020-04-15","cited_by_count":59},{"id":"2009.03728","title":"Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective","created":"2020-09-08","cited_by_count":59},{"id":"2102.04716","title":"Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training","created":"2021-02-09","cited_by_count":59},{"id":"2109.02355","title":"A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning","created":"2021-09-06","cited_by_count":57},{"id":"2212.10986","title":"SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning","created":"2022-12-21","cited_by_count":51},{"id":"2104.02703","title":"Adversarial Robustness under Long-Tailed Distribution","created":"2021-04-06","cited_by_count":50}],"next_cursor":"100"}