{"list":"other","total":63,"rows":[{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"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":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"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":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"1412.1897","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","created":"2014-12-05","cited_by_count":776},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"1412.3756","title":"Certifying and removing disparate impact","created":"2014-12-11","cited_by_count":715},{"id":"1708.06131","title":"Evasion Attacks against Machine Learning at Test Time","created":"2017-08-21","cited_by_count":689},{"id":"1610.07524","title":"Fair prediction with disparate impact: A study of bias in recidivism prediction instruments","created":"2016-10-24","cited_by_count":672},{"id":"1609.05807","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","created":"2016-09-19","cited_by_count":586},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560},{"id":"1804.08598","title":"Black-box Adversarial Attacks with Limited Queries and Information","created":"2018-04-23","cited_by_count":501},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"1712.04248","title":"Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models","created":"2017-12-12","cited_by_count":462},{"id":"1712.03141","title":"Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning","created":"2017-12-08","cited_by_count":414},{"id":"1709.02012","title":"On Fairness and Calibration","created":"2017-09-06","cited_by_count":406},{"id":"1701.08230","title":"Algorithmic decision making and the cost of fairness","created":"2017-01-28","cited_by_count":403},{"id":"2001.00973","title":"Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing","created":"2020-01-03","cited_by_count":384},{"id":"1610.08452","title":"Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment","created":"2016-10-26","cited_by_count":369},{"id":"1703.09207","title":"Fairness in Criminal Justice Risk Assessments: The State of the Art","created":"2017-03-27","cited_by_count":315},{"id":"2210.04610","title":"Red-Teaming the Stable Diffusion Safety Filter","created":"2022-10-03","cited_by_count":264},{"id":"2407.06460","title":"MUSE: Machine Unlearning Six-Way Evaluation for Language Models","created":"2024-07-08","cited_by_count":261},{"id":"2011.07876","title":"A Survey on the Explainability of Supervised Machine Learning","created":"2020-11-16","cited_by_count":227},{"id":"2006.07709","title":"Auditing Differentially Private Machine Learning: How Private is Private SGD?","created":"2020-06-13","cited_by_count":218},{"id":"2002.02770","title":"A Survey on Causal Inference","created":"2020-02-05","cited_by_count":202},{"id":"1511.05897","title":"Censoring Representations with an Adversary","created":"2015-11-18","cited_by_count":192},{"id":"2204.01075","title":"Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI","created":"2022-04-03","cited_by_count":171},{"id":"1810.08810","title":"The Frontiers of Fairness in Machine Learning","created":"2018-10-20","cited_by_count":141},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126},{"id":"1301.6822","title":"Discrimination in Online Ad Delivery","created":"2013-01-29","cited_by_count":93},{"id":"1408.6491","title":"Automated Experiments on Ad Privacy Settings: A Tale of Opacity, Choice, and Discrimination","created":"2014-08-27","cited_by_count":83},{"id":"2401.15897","title":"Red-Teaming for Generative AI: Silver Bullet or Security Theater?","created":"2024-01-29","cited_by_count":83},{"id":"2206.04737","title":"Outsider Oversight: Designing a Third Party Audit Ecosystem for AI Governance","created":"2022-06-09","cited_by_count":67},{"id":"2302.04237","title":"Black Box Adversarial Prompting for Foundation Models","created":"2023-02-08","cited_by_count":62},{"id":"2204.05239","title":"Exploring the Universal Vulnerability of Prompt-based Learning Paradigm","created":"2022-04-11","cited_by_count":57},{"id":"2310.02521","title":"Who Audits the Auditors? Recommendations from a field scan of the algorithmic auditing ecosystem","created":"2023-10-04","cited_by_count":52},{"id":"1906.09218","title":"FlipTest: Fairness Testing via Optimal Transport","created":"2019-06-21","cited_by_count":51},{"id":"2403.12958","title":"Dated Data: Tracing Knowledge Cutoffs in Large Language Models","created":"2024-03-19","cited_by_count":51},{"id":"1602.07043","title":"Auditing Black-box Models for Indirect Influence","created":"2016-02-23","cited_by_count":41},{"id":"2110.11010","title":"Algorithmic Amplification of Politics on Twitter","created":"2021-10-21","cited_by_count":38},{"id":"1501.06307","title":"It's a Man's Wikipedia? Assessing Gender Inequality in an Online Encyclopedia","created":"2015-01-26","cited_by_count":30},{"id":"2102.04256","title":"Problematic Machine Behavior: A Systematic Literature Review of Algorithm Audits","created":"2021-02-03","cited_by_count":21},{"id":"1706.05011","title":"Measuring Personalization of Web Search","created":"2017-06-15","cited_by_count":20},{"id":"2003.05048","title":"Auditing ML Models for Individual Bias and Unfairness","created":"2020-03-11","cited_by_count":18},{"id":"2404.04500","title":"Trustless Audits without Revealing Data or Models","created":"2024-04-06","cited_by_count":15},{"id":"2103.16714","title":"Statistical inference for individual fairness","created":"2021-03-30","cited_by_count":13},{"id":"2308.15768","title":"Sociotechnical Audits: Broadening the Algorithm Auditing Lens to Investigate Targeted Advertising","created":"2023-08-30","cited_by_count":12},{"id":"2002.04049","title":"Guidelines for Implementing and Auditing Differentially Private Systems","created":"2020-02-10","cited_by_count":10},{"id":"2308.10398","title":"Causally estimating the effect of YouTube's recommender system using counterfactual bots","created":"2023-08-21","cited_by_count":8},{"id":"2110.03443","title":"Unpacking the Black Box: Regulating Algorithmic Decisions","created":"2021-10-05","cited_by_count":3},{"id":"2401.11194","title":"WEIRD Audits? Research Trends, Linguistic and Geographical Disparities in the Algorithm Audits of Online Platforms -- A Systematic Literature Review","created":"2024-01-20","cited_by_count":3},{"id":"2212.13995","title":"The Right to be an Exception to a Data-Driven Rule","created":"2022-12-28","cited_by_count":2},{"id":"2304.10525","title":"A User-Driven Framework for Regulating and Auditing Social Media","created":"2023-04-20","cited_by_count":1}],"next_cursor":null}