{"list":"other","total":77,"rows":[{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"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":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"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":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"1709.02012","title":"On Fairness and Calibration","created":"2017-09-06","cited_by_count":406},{"id":"2010.04053","title":"Fairness in Machine Learning: A Survey","created":"2020-10-04","cited_by_count":370},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367},{"id":"1610.05755","title":"Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data","created":"2016-10-18","cited_by_count":348},{"id":"1809.06514","title":"Actionable Recourse in Linear Classification","created":"2018-09-18","cited_by_count":328},{"id":"1905.12101","title":"Differential Privacy Has Disparate Impact on Model Accuracy","created":"2019-05-28","cited_by_count":316},{"id":"1802.08908","title":"Scalable Private Learning with PATE","created":"2018-02-24","cited_by_count":269},{"id":"1802.04422","title":"A comparative study of fairness-enhancing interventions in machine learning","created":"2018-02-13","cited_by_count":208},{"id":"2002.11097","title":"Problems with Shapley-value-based explanations as feature importance measures","created":"2020-02-25","cited_by_count":200},{"id":"1706.02744","title":"Avoiding Discrimination through Causal Reasoning","created":"2017-06-08","cited_by_count":194},{"id":"2007.07646","title":"A Survey of Privacy Attacks in Machine Learning","created":"2020-07-15","cited_by_count":146},{"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":"1909.07913","title":"Learning to Deceive with Attention-Based Explanations","created":"2019-09-17","cited_by_count":111},{"id":"1911.06473","title":"\"How do I fool you?\": Manipulating User Trust via Misleading Black Box Explanations","created":"2019-11-15","cited_by_count":111},{"id":"1807.05185","title":"Model Reconstruction from Model Explanations","created":"2018-07-13","cited_by_count":86},{"id":"2011.03731","title":"On the Privacy Risks of Algorithmic Fairness","created":"2020-11-07","cited_by_count":82},{"id":"1901.09749","title":"Fairwashing: the risk of rationalization","created":"2019-01-28","cited_by_count":81},{"id":"1812.02696","title":"Differentially Private Fair Learning","created":"2018-12-06","cited_by_count":76},{"id":"1412.7584","title":"Differential Privacy and Machine Learning: a Survey and Review","created":"2014-12-24","cited_by_count":67},{"id":"2009.06389","title":"Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy","created":"2020-09-10","cited_by_count":61},{"id":"1905.12744","title":"Fair Decision Making using Privacy-Protected Data","created":"2019-05-29","cited_by_count":58},{"id":"1909.03166","title":"Equalizing Recourse across Groups","created":"2019-09-07","cited_by_count":55},{"id":"2009.12562","title":"Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach","created":"2020-09-26","cited_by_count":53},{"id":"2104.12669","title":"Exploiting Explanations for Model Inversion Attacks","created":"2021-04-26","cited_by_count":49},{"id":"2009.01884","title":"Model extraction from counterfactual explanations","created":"2020-09-03","cited_by_count":47},{"id":"2202.08187","title":"Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey","created":"2022-02-16","cited_by_count":47},{"id":"2002.11651","title":"Fair Learning with Private Demographic Data","created":"2020-02-26","cited_by_count":46},{"id":"2005.04176","title":"In Pursuit of Interpretable, Fair and Accurate Machine Learning for Criminal Recidivism Prediction","created":"2020-05-08","cited_by_count":42},{"id":"1806.03281","title":"Blind Justice: Fairness with Encrypted Sensitive Attributes","created":"2018-06-08","cited_by_count":41},{"id":"2205.03295","title":"The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations","created":"2022-05-06","cited_by_count":41},{"id":"2205.07277","title":"Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations","created":"2022-05-15","cited_by_count":40},{"id":"2005.08679","title":"An Overview of Privacy in Machine Learning","created":"2020-05-18","cited_by_count":39},{"id":"2010.06667","title":"Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings","created":"2020-10-13","cited_by_count":37},{"id":"1906.00389","title":"Disparate Vulnerability to Membership Inference Attacks","created":"2019-06-02","cited_by_count":35},{"id":"2107.08909","title":"MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AI","created":"2021-07-19","cited_by_count":35},{"id":"2010.07389","title":"Explainability for fair machine learning","created":"2020-10-14","cited_by_count":34},{"id":"2106.12576","title":"DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?","created":"2021-06-22","cited_by_count":33},{"id":"2205.06504","title":"DualCF: Efficient Model Extraction Attack from Counterfactual Explanations","created":"2022-05-13","cited_by_count":32},{"id":"1906.02004","title":"Interpretable and Differentially Private Predictions","created":"2019-06-05","cited_by_count":28},{"id":"2010.13764","title":"Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability","created":"2020-10-26","cited_by_count":25},{"id":"2006.09129","title":"Model Explanations with Differential Privacy","created":"2020-06-16","cited_by_count":23},{"id":"2106.07504","title":"Characterizing the risk of fairwashing","created":"2021-06-14","cited_by_count":21},{"id":"2001.04958","title":"Differentially Private and Fair Classification via Calibrated Functional Mechanism","created":"2020-01-14","cited_by_count":20},{"id":"2210.16242","title":"Differential Privacy has Bounded Impact on Fairness in Classification","created":"2022-10-28","cited_by_count":18},{"id":"1611.01919","title":"Decision Tree Classification with Differential Privacy: A Survey","created":"2016-11-07","cited_by_count":17},{"id":"1809.04578","title":"Simplicity Creates Inequity: Implications for Fairness, Stereotypes, and Interpretability","created":"2018-09-12","cited_by_count":16},{"id":"2012.03812","title":"Improving Fairness and Privacy in Selection Problems","created":"2020-12-07","cited_by_count":16},{"id":"2208.09967","title":"Inferring Sensitive Attributes from Model Explanations","created":"2022-08-21","cited_by_count":15},{"id":"2208.02878","title":"Differentially Private Counterfactuals via Functional Mechanism","created":"2022-08-04","cited_by_count":13},{"id":"2109.08630","title":"A Fairness Analysis on Private Aggregation of Teacher Ensembles","created":"2021-09-17","cited_by_count":11},{"id":"2212.04454","title":"XRand: Differentially Private Defense against Explanation-Guided Attacks","created":"2022-12-08","cited_by_count":11},{"id":"2206.03585","title":"XAI for Cybersecurity: State of the Art, Challenges, Open Issues and Future Directions","created":"2022-06-03","cited_by_count":10},{"id":"2209.01215","title":"Exploiting Fairness to Enhance Sensitive Attributes Reconstruction","created":"2022-09-02","cited_by_count":10},{"id":"2106.13203","title":"When Differential Privacy Meets Interpretability: A Case Study","created":"2021-06-24","cited_by_count":8},{"id":"2106.13346","title":"What will it take to generate fairness-preserving explanations?","created":"2021-06-24","cited_by_count":7},{"id":"2308.15099","title":"Probabilistic Dataset Reconstruction from Interpretable Models","created":"2023-08-29","cited_by_count":7},{"id":"2302.08044","title":"Balancing Privacy Protection and Interpretability in Federated Learning","created":"2023-02-16","cited_by_count":6},{"id":"1810.00024","title":"Explainable Black-Box Attacks Against Model-based Authentication","created":"2018-09-28","cited_by_count":5},{"id":"2102.03785","title":"Robust Explanations for Private Support Vector Machines","created":"2021-02-07","cited_by_count":4},{"id":"1910.01432","title":"The Bouncer Problem: Challenges to Remote Explainability","created":"2019-10-03","cited_by_count":3},{"id":"2106.12563","title":"Feature Attributions and Counterfactual Explanations Can Be Manipulated","created":"2021-06-23","cited_by_count":2}],"next_cursor":null}