{"total":60,"rows":[{"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":"2108.04974","title":"SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)","created":"2021-08-11","cited_by_count":69,"area":null},{"id":"2202.08602","title":"Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations","created":"2022-02-17","cited_by_count":61,"area":null},{"id":"2112.08331","title":"Model Stealing Attacks Against Inductive Graph Neural Networks","created":"2021-12-15","cited_by_count":50,"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":"2111.09999","title":"TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems","created":"2021-11-19","cited_by_count":36,"area":null},{"id":"2112.12982","title":"Parameter identifiability of a deep feedforward ReLU neural network","created":"2021-12-24","cited_by_count":24,"area":null},{"id":"2201.05889","title":"StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning","created":"2022-01-15","cited_by_count":23,"area":null},{"id":"2404.00473","title":"Privacy Backdoors: Stealing Data with Corrupted Pretrained Models","created":"2024-03-30","cited_by_count":22,"area":null},{"id":"2107.09370","title":"An Embedding of ReLU Networks and an Analysis of their Identifiability","created":"2021-07-20","cited_by_count":20,"area":null},{"id":"2304.06607","title":"False Claims against Model Ownership Resolution","created":"2023-04-13","cited_by_count":17,"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":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2106.12478","title":"Teacher Model Fingerprinting Attacks Against Transfer Learning","created":"2021-06-23","cited_by_count":16,"area":null},{"id":"2304.08566","title":"GrOVe: Ownership Verification of Graph Neural Networks using Embeddings","created":"2023-04-17","cited_by_count":16,"area":null},{"id":"2206.07424","title":"Local Identifiability of Deep ReLU Neural Networks: the Theory","created":"2022-06-15","cited_by_count":12,"area":null},{"id":"2207.01991","title":"Conflicting Interactions Among Protection Mechanisms for Machine Learning Models","created":"2022-07-05","cited_by_count":12,"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":"2202.13351","title":"Split HE: Fast Secure Inference Combining Split Learning and Homomorphic Encryption","created":"2022-02-27","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":"2211.05590","title":"A Practical Introduction to Side-Channel Extraction of Deep Neural Network Parameters","created":"2022-11-10","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":"2107.09546","title":"Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions","created":"2021-07-20","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":"2110.15444","title":"10 Security and Privacy Problems in Large Foundation Models","created":"2021-10-28","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":"2101.10865","title":"On managing vulnerabilities in AI/ML systems","created":"2021-01-22","cited_by_count":5,"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":"2302.11982","title":"A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots","created":"2023-02-23","cited_by_count":5,"area":null},{"id":"2308.16703","title":"Fault Injection and Safe-Error Attack for Extraction of Embedded Neural Network Models","created":"2023-08-31","cited_by_count":5,"area":null},{"id":"2105.01401","title":"A Review of Confidentiality Threats Against Embedded Neural Network Models","created":"2021-05-04","cited_by_count":4,"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":"2302.01584","title":"TT-TFHE: a Torus Fully Homomorphic Encryption-Friendly Neural Network Architecture","created":"2023-02-03","cited_by_count":4,"area":null},{"id":"2310.01959","title":"Beyond Labeling Oracles: What does it mean to steal ML models?","created":"2023-10-03","cited_by_count":4,"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":"2302.06361","title":"Dash: Accelerating Distributed Private Convolutional Neural Network Inference with Arithmetic Garbled Circuits","created":"2023-02-13","cited_by_count":2,"area":null},{"id":"2307.01292","title":"Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems","created":"2023-07-03","cited_by_count":2,"area":null},{"id":"2311.01344","title":"Like an Open Book? Read Neural Network Architecture with Simple Power Analysis on 32-bit Microcontrollers","created":"2023-11-02","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":"2509.20714","title":"Cryptographic Backdoor for Neural Networks: Boon and Bane","created":"2025-09-25","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":"2605.04901","title":"On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference","created":"2026-05-06","cited_by_count":2,"area":null},{"id":"2108.12579","title":"Power-Based Attacks on Spatial DNN Accelerators","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2204.06241","title":"Stealing and Evading Malware Classifiers and Antivirus at Low False Positive Conditions","created":"2022-04-13","cited_by_count":1,"area":null},{"id":"2205.02511","title":"One Picture is Worth a Thousand Words: A New Wallet Recovery Process","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2206.14371","title":"Matryoshka: Stealing Functionality of Private ML Data by Hiding Models in Model","created":"2022-06-29","cited_by_count":0,"area":null},{"id":"2209.06373","title":"SEEK: model extraction attack against hybrid secure inference protocols","created":"2022-09-14","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":"2401.11723","title":"Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Them","created":"2024-01-22","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":"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":"2511.20312","title":"Data Augmentation Techniques to Reverse-Engineer Neural Network Weights from Input-Output Queries","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2606.04317","title":"Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2608.06631","title":"Cryptanalytic Extraction of Isolated Bias-Free GLU Feed-Forward Blocks by Antipodal Separation","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.28843","title":"Curvature Cryptanalysis of Smooth Transformer Feed-Forward Networks","created":"2026-08-28","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":"2610.16790","title":"Logit Leakage through Floating-Point Bias Addition","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}