{"list":"other","total":54,"rows":[{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"1702.01135","title":"Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks","created":"2017-02-03","cited_by_count":744},{"id":"1711.00851","title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","created":"2017-11-02","cited_by_count":567},{"id":"1802.03471","title":"Certified Robustness to Adversarial Examples with Differential Privacy","created":"2018-02-09","cited_by_count":468},{"id":"1811.00866","title":"Efficient Neural Network Robustness Certification with General Activation Functions","created":"2018-11-02","cited_by_count":445},{"id":"1906.04584","title":"Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers","created":"2019-06-09","cited_by_count":330},{"id":"1804.04368","title":"Regularisation of Neural Networks by Enforcing Lipschitz Continuity","created":"2018-04-12","cited_by_count":314},{"id":"1801.09344","title":"Certified Defenses against Adversarial Examples","created":"2018-01-29","cited_by_count":306},{"id":"1704.08847","title":"Parseval Networks: Improving Robustness to Adversarial Examples","created":"2017-04-28","cited_by_count":293},{"id":"1610.06940","title":"Safety Verification of Deep Neural Networks","created":"2016-10-21","cited_by_count":263},{"id":"1804.09699","title":"Towards Fast Computation of Certified Robustness for ReLU Networks","created":"2018-04-25","cited_by_count":255},{"id":"1705.01320","title":"Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks","created":"2017-05-03","cited_by_count":242},{"id":"1811.05381","title":"Sorting out Lipschitz function approximation","created":"2018-11-13","cited_by_count":213},{"id":"1906.06316","title":"Towards Stable and Efficient Training of Verifiably Robust Neural Networks","created":"2019-06-14","cited_by_count":205},{"id":"2011.13824","title":"Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers","created":"2020-11-27","cited_by_count":187},{"id":"1705.08475","title":"Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation","created":"2017-05-23","cited_by_count":185},{"id":"1804.10829","title":"Formal Security Analysis of Neural Networks using Symbolic Intervals","created":"2018-04-28","cited_by_count":185},{"id":"1801.10578","title":"Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach","created":"2018-01-31","cited_by_count":182},{"id":"1809.03113","title":"Certified Adversarial Robustness with Additive Noise","created":"2018-09-10","cited_by_count":180},{"id":"1811.01057","title":"Semidefinite relaxations for certifying robustness to adversarial examples","created":"2018-11-02","cited_by_count":179},{"id":"1809.08098","title":"Efficient Formal Safety Analysis of Neural Networks","created":"2018-09-19","cited_by_count":165},{"id":"2002.08118","title":"Randomized Smoothing of All Shapes and Sizes","created":"2020-02-19","cited_by_count":147},{"id":"1907.02610","title":"Adversarial Robustness through Local Linearization","created":"2019-07-04","cited_by_count":146},{"id":"1805.12514","title":"Scaling provable adversarial defenses","created":"2018-05-31","cited_by_count":143},{"id":"1706.07351","title":"An approach to reachability analysis for feed-forward ReLU neural networks","created":"2017-06-22","cited_by_count":127},{"id":"1803.06567","title":"A Dual Approach to Scalable Verification of Deep Networks","created":"2018-03-17","cited_by_count":125},{"id":"1902.08722","title":"A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks","created":"2019-02-23","cited_by_count":125},{"id":"1807.07838","title":"TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time","created":"2018-07-20","cited_by_count":108},{"id":"2102.08452","title":"Globally-Robust Neural Networks","created":"2021-02-16","cited_by_count":108},{"id":"2009.04131","title":"SoK: Certified Robustness for Deep Neural Networks","created":"2020-09-09","cited_by_count":105},{"id":"2005.02929","title":"Training robust neural networks using Lipschitz bounds","created":"2020-05-06","cited_by_count":99},{"id":"1908.05164","title":"Unconstrained Monotonic Neural Networks","created":"2019-08-14","cited_by_count":92},{"id":"1811.07457","title":"Generalizable Adversarial Training via Spectral Normalization","created":"2018-11-19","cited_by_count":68},{"id":"1912.09899","title":"Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing","created":"2019-12-20","cited_by_count":54},{"id":"1805.10265","title":"Training verified learners with learned verifiers","created":"2018-05-25","cited_by_count":50},{"id":"1811.12395","title":"CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks","created":"2018-11-29","cited_by_count":50},{"id":"1905.11468","title":"Scaleable input gradient regularization for adversarial robustness","created":"2019-05-27","cited_by_count":47},{"id":"1509.07892","title":"Evasion and Hardening of Tree Ensemble Classifiers","created":"2015-09-25","cited_by_count":44},{"id":"2007.10868","title":"Scaling Polyhedral Neural Network Verification on GPUs","created":"2020-07-20","cited_by_count":43},{"id":"1606.04435","title":"Adversarial Perturbations Against Deep Neural Networks for Malware Classification","created":"2016-06-14","cited_by_count":42},{"id":"2002.11002","title":"Turning 30: New Ideas in Inductive Logic Programming","created":"2020-02-25","cited_by_count":42},{"id":"1505.06378","title":"Monotonic Calibrated Interpolated Look-Up Tables","created":"2015-05-23","cited_by_count":35},{"id":"1712.06174","title":"Deep Neural Networks as 0-1 Mixed Integer Linear Programs: A Feasibility Study","created":"2017-12-17","cited_by_count":25},{"id":"1909.11542","title":"CLN2INV: Learning Loop Invariants with Continuous Logic Networks","created":"2019-09-25","cited_by_count":20},{"id":"1510.07338","title":"Reviewer Integration and Performance Measurement for Malware Detection","created":"2015-10-26","cited_by_count":19},{"id":"1904.03542","title":"On Training Robust PDF Malware Classifiers","created":"2019-04-06","cited_by_count":19},{"id":"2003.07959","title":"Learning Nonlinear Loop Invariants with Gated Continuous Logic Networks (Extended Version)","created":"2020-03-17","cited_by_count":17},{"id":"1907.10662","title":"ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks","created":"2019-07-17","cited_by_count":14},{"id":"1904.04861","title":"Universal Lipschitz Approximation in Bounded Depth Neural Networks","created":"2019-04-09","cited_by_count":11},{"id":"2102.01208","title":"Fast Training of Provably Robust Neural Networks by SingleProp","created":"2021-02-01","cited_by_count":5}],"next_cursor":null}