{"total":82,"rows":[{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737,"area":null},{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133,"area":null},{"id":"2206.08451","title":"I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences","created":"2022-06-16","cited_by_count":75,"area":null},{"id":"2204.11022","title":"Towards Data-Free Model Stealing in a Hard Label Setting","created":"2022-04-23","cited_by_count":58,"area":null},{"id":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53,"area":null},{"id":"2104.12669","title":"Exploiting Explanations for Model Inversion Attacks","created":"2021-04-26","cited_by_count":49,"area":null},{"id":"2107.01614","title":"Survey: Leakage and Privacy at Inference Time","created":"2021-07-04","cited_by_count":44,"area":null},{"id":"2111.04625","title":"DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories","created":"2021-11-08","cited_by_count":42,"area":null},{"id":"2306.06179","title":"Hidden symmetries of ReLU networks","created":"2023-06-09","cited_by_count":39,"area":null},{"id":"2107.08909","title":"MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AI","created":"2021-07-19","cited_by_count":35,"area":null},{"id":"2403.10415","title":"Gradient based Feature Attribution in Explainable AI: A Technical Review","created":"2024-03-15","cited_by_count":34,"area":null},{"id":"2205.06504","title":"DualCF: Efficient Model Extraction Attack from Counterfactual Explanations","created":"2022-05-13","cited_by_count":32,"area":null},{"id":"2202.05258","title":"Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2106.07504","title":"Characterizing the risk of fairwashing","created":"2021-06-14","cited_by_count":21,"area":null},{"id":"2109.03285","title":"Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud","created":"2021-09-07","cited_by_count":19,"area":null},{"id":"2303.04729","title":"Stealing the Decoding Algorithms of Language Models","created":"2023-03-08","cited_by_count":19,"area":null},{"id":"2310.08708","title":"Polynomial Time Cryptanalytic Extraction of Neural Network Models","created":"2023-10-12","cited_by_count":17,"area":null},{"id":"2208.09967","title":"Inferring Sensitive Attributes from Model Explanations","created":"2022-08-21","cited_by_count":15,"area":null},{"id":"2405.05369","title":"Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory","created":"2024-05-08","cited_by_count":14,"area":null},{"id":"2208.02878","title":"Differentially Private Counterfactuals via Functional Mechanism","created":"2022-08-04","cited_by_count":13,"area":null},{"id":"2105.09673","title":"An Exact Poly-Time Membership-Queries Algorithm for Extraction a three-Layer ReLU Network","created":"2021-05-20","cited_by_count":11,"area":null},{"id":"2212.04454","title":"XRand: Differentially Private Defense against Explanation-Guided Attacks","created":"2022-12-08","cited_by_count":11,"area":null},{"id":"2302.08466","title":"Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public Data","created":"2023-02-16","cited_by_count":11,"area":null},{"id":"2109.10870","title":"SoK: Machine Learning Governance","created":"2021-09-20","cited_by_count":10,"area":null},{"id":"2308.00958","title":"Isolation and Induction: Training Robust Deep Neural Networks against Model Stealing Attacks","created":"2023-08-02","cited_by_count":10,"area":null},{"id":"2302.02162","title":"AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Interpretable Models","created":"2023-02-04","cited_by_count":9,"area":null},{"id":"2303.12942","title":"A Survey on Explainable Artificial Intelligence for Cybersecurity","created":"2023-03-07","cited_by_count":9,"area":null},{"id":"2407.11359","title":"Feature Inference Attack on Shapley Values","created":"2024-07-16","cited_by_count":9,"area":null},{"id":"2410.05750","title":"Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2101.02069","title":"Model Extraction and Defenses on Generative Adversarial Networks","created":"2021-01-06","cited_by_count":8,"area":null},{"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,"area":null},{"id":"2210.17376","title":"SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2406.10011","title":"Beyond Slow Signs in High-fidelity Model Extraction","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2102.01979","title":"Key Technology Considerations in Developing and Deploying Machine Learning Models in Clinical Radiology Practice","created":"2021-02-03","cited_by_count":6,"area":null},{"id":"2111.04727","title":"Efficiently Learning Any One Hidden Layer ReLU Network From Queries","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2111.14838","title":"Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification","created":"2021-11-29","cited_by_count":6,"area":null},{"id":"2310.14047","title":"MeaeQ: Mount Model Extraction Attacks with Efficient Queries","created":"2023-10-21","cited_by_count":6,"area":null},{"id":"2404.00673","title":"A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures","created":"2024-03-31","cited_by_count":6,"area":null},{"id":"2210.03297","title":"Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems","created":"2022-10-07","cited_by_count":5,"area":null},{"id":"2303.08581","title":"Model Extraction Attacks on Split Federated Learning","created":"2023-03-13","cited_by_count":5,"area":null},{"id":"2308.04341","title":"Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage","created":"2023-08-08","cited_by_count":5,"area":null},{"id":"2311.14137","title":"Privacy-Preserving Algorithmic Recourse","created":"2023-11-23","cited_by_count":5,"area":null},{"id":"2209.04022","title":"Privacy of Autonomous Vehicles: Risks, Protection Methods, and Future Directions","created":"2022-09-08","cited_by_count":4,"area":null},{"id":"2305.00322","title":"Toward $L_\\infty$-recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields","created":"2023-04-29","cited_by_count":4,"area":null},{"id":"2312.16191","title":"SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning","created":"2023-12-22","cited_by_count":4,"area":null},{"id":"2505.05707","title":"Crowding Out The Noise: Algorithmic Collective Action Under Differential Privacy","created":"2025-05-09","cited_by_count":4,"area":null},{"id":"2108.13930","title":"EG-Booster: Explanation-Guided Booster of ML Evasion Attacks","created":"2021-08-31","cited_by_count":3,"area":null},{"id":"2202.11266","title":"Margin-distancing for safe model explanation","created":"2022-02-23","cited_by_count":3,"area":null},{"id":"2406.15789","title":"Privacy Implications of Explainable AI in Data-Driven Systems","created":"2024-06-22","cited_by_count":3,"area":null},{"id":"2502.05325","title":"From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks","created":"2025-02-07","cited_by_count":3,"area":null},{"id":"2506.17047","title":"Navigating the Deep: End-to-End Extraction on Deep Neural Networks","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2508.19641","title":"Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2305.12167","title":"The Case Against Explainability","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2406.02027","title":"Inference Attacks: A Taxonomy, Survey, and Promising Directions","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2502.18077","title":"Examining the Threat Landscape: Foundation Models and Model Stealing","created":"2025-02-25","cited_by_count":2,"area":null},{"id":"2505.02828","title":"Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Review","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2510.06692","title":"Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial?","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2602.09748","title":"Linear Model Extraction via Factual and Counterfactual Queries","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2608.03294","title":"Provably Learning Multi-Head Attention with Queries","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2103.06797","title":"BODAME: Bilevel Optimization for Defense Against Model Extraction","created":"2021-03-11","cited_by_count":1,"area":null},{"id":"2111.15160","title":"Mitigating Adversarial Attacks by Distributing Different Copies to Different Users","created":"2021-11-30","cited_by_count":1,"area":null},{"id":"2305.05869","title":"Finding Meaningful Distributions of ML Black-boxes under Forensic Investigation","created":"2023-05-10","cited_by_count":1,"area":null},{"id":"2404.03348","title":"Knowledge Distillation-Based Model Extraction Attack using GAN-based Private Counterfactual Explanations","created":"2024-04-04","cited_by_count":1,"area":null},{"id":"2411.13459","title":"SoK: A Systems Perspective on Compound AI Threats and Countermeasures","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2502.15567","title":"Model Privacy: A Unified Framework for Understanding Model Stealing Attacks and Defenses","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2506.03087","title":"Do Explanations Increase the Risk of Decision Logic Leakage? Explanation-Guided Stealing of Graph Models","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2507.04528","title":"Towards integration of Privacy Enhancing Technologies in Explainable Artificial Intelligence","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2601.16873","title":"Provably Learning Attention with Queries","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2606.08173","title":"AI-Native Closed-Loop Security for 6G-Enabled Cyber-Physical Systems: From Edge Detection to Network-Wide Mitigation","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2212.07508","title":"Tensions Between the Proxies of Human Values in AI","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2312.04675","title":"Reverse Engineering Deep ReLU Networks An Optimization-based Algorithm","created":"2023-12-07","cited_by_count":0,"area":null},{"id":"2312.07040","title":"Rethinking Model Inversion Attacks With Patch-Wise Reconstruction","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2406.00249","title":"Privacy Challenges in Meta-Learning: An Investigation on Model-Agnostic Meta-Learning","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2409.08919","title":"XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2411.10174","title":"A Divide-and-Conquer Strategy for Hard-Label Extraction of Deep Neural Networks via Side-Channel Attacks","created":"2024-11-15","cited_by_count":0,"area":null},{"id":"2503.06188","title":"Attackers Can Do Better: Over- and Understated Factors of Model Stealing Attacks","created":"2025-03-08","cited_by_count":0,"area":null},{"id":"2508.21654","title":"I Stolenly Swear That I Am Up to (No) Good: Design and Evaluation of Model Stealing Attacks","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2509.16546","title":"Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2605.30470","title":"Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2609.10627","title":"SoK: Privacy Attacks on Machine Learning via Explainable AI","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.21941","title":"End-to-End Hard-Label Cryptanalytic Model Extraction Using Efficient Sign Recovery","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.31643","title":"Information Design Against Gaming and Learning Adversaries","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}