{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"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":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"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":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"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":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"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":"2009.07896","title":"Captum: A unified and generic model interpretability library for PyTorch","created":"2020-09-16","cited_by_count":547},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367},{"id":"1806.08049","title":"On the Robustness of Interpretability Methods","created":"2018-06-21","cited_by_count":314},{"id":"1901.04592","title":"Interpretable machine learning: definitions, methods, and applications","created":"2019-01-14","cited_by_count":305},{"id":"1605.01713","title":"Not Just a Black Box: Learning Important Features Through Propagating Activation Differences","created":"2016-05-05","cited_by_count":297},{"id":"1801.02613","title":"Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality","created":"2018-01-08","cited_by_count":282},{"id":"1703.00410","title":"Detecting Adversarial Samples from Artifacts","created":"2017-03-01","cited_by_count":245},{"id":"1910.07969","title":"On Completeness-aware Concept-Based Explanations in Deep Neural Networks","created":"2019-10-17","cited_by_count":239},{"id":"1906.07983","title":"Explanations can be manipulated and geometry is to blame","created":"2019-06-19","cited_by_count":216},{"id":"2005.00631","title":"Evaluating and Aggregating Feature-based Model Explanations","created":"2020-05-01","cited_by_count":188},{"id":"2202.06861","title":"Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond","created":"2022-02-14","cited_by_count":171},{"id":"1909.03012","title":"One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques","created":"2019-09-06","cited_by_count":164},{"id":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136},{"id":"1610.00768","title":"Technical Report on the CleverHans v2.1.0 Adversarial Examples Library","created":"2016-10-03","cited_by_count":124},{"id":"1902.02041","title":"Fooling Neural Network Interpretations via Adversarial Model Manipulation","created":"2019-02-06","cited_by_count":112},{"id":"1912.05100","title":"Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches","created":"2019-12-11","cited_by_count":101},{"id":"2002.01092","title":"Human-centered Explainable AI: Towards a Reflective Sociotechnical Approach","created":"2020-02-04","cited_by_count":90},{"id":"1807.05185","title":"Model Reconstruction from Model Explanations","created":"2018-07-13","cited_by_count":86},{"id":"1712.00547","title":"Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences","created":"2017-12-02","cited_by_count":85},{"id":"1705.05598","title":"Learning how to explain neural networks: PatternNet and PatternAttribution","created":"2017-05-16","cited_by_count":84},{"id":"1905.04172","title":"On the Connection Between Adversarial Robustness and Saliency Map Interpretability","created":"2019-05-10","cited_by_count":80},{"id":"1812.00891","title":"Interpretable Deep Learning under Fire","created":"2018-12-03","cited_by_count":74},{"id":"2203.06877","title":"Rethinking Stability for Attribution-based Explanations","created":"2022-03-14","cited_by_count":52},{"id":"1803.10266","title":"Privacy-preserving Prediction","created":"2018-03-27","cited_by_count":48},{"id":"1906.03499","title":"ML-LOO: Detecting Adversarial Examples with Feature Attribution","created":"2019-06-08","cited_by_count":48},{"id":"2107.11400","title":"Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks","created":"2021-07-23","cited_by_count":48},{"id":"1906.02108","title":"Evaluating Explanation Methods for Deep Learning in Security","created":"2019-06-05","cited_by_count":38},{"id":"1906.02004","title":"Interpretable and Differentially Private Predictions","created":"2019-06-05","cited_by_count":28},{"id":"2106.10185","title":"NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights","created":"2021-06-18","cited_by_count":28},{"id":"2006.09129","title":"Model Explanations with Differential Privacy","created":"2020-06-16","cited_by_count":23},{"id":"2208.10605","title":"SoK: Explainable Machine Learning for Computer Security Applications","created":"2022-08-22","cited_by_count":20},{"id":"2109.11495","title":"DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications","created":"2021-09-23","cited_by_count":18},{"id":"1807.04178","title":"Explainable Security","created":"2018-07-11","cited_by_count":15},{"id":"1708.02368","title":"Automatic feature learning for vulnerability prediction","created":"2017-08-08","cited_by_count":10},{"id":"1903.05821","title":"Attribution-driven Causal Analysis for Detection of Adversarial Examples","created":"2019-03-14","cited_by_count":8},{"id":"2206.14004","title":"On the amplification of security and privacy risks by post-hoc explanations in machine learning models","created":"2022-06-28","cited_by_count":8},{"id":"2209.01782","title":"\"Is your explanation stable?\": A Robustness Evaluation Framework for Feature Attribution","created":"2022-09-05","cited_by_count":7}],"next_cursor":null}