{"total":214,"rows":[{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133,"area":null},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116,"area":"safety"},{"id":"2102.05429","title":"Node-Level Membership Inference Attacks Against Graph Neural Networks","created":"2021-02-10","cited_by_count":84,"area":null},{"id":"2103.05633","title":"Proof-of-Learning: Definitions and Practice","created":"2021-03-09","cited_by_count":84,"area":null},{"id":"2101.06570","title":"Membership Inference Attack on Graph Neural Networks","created":"2021-01-17","cited_by_count":81,"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":"2303.11165","title":"Computationally Budgeted Continual Learning: What Does Matter?","created":"2023-03-20","cited_by_count":61,"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":"2109.08045","title":"Membership Inference Attacks Against Recommender Systems","created":"2021-09-16","cited_by_count":57,"area":"safety"},{"id":"2212.14315","title":"\"Real Attackers Don't Compute Gradients\": Bridging the Gap Between Adversarial ML Research and Practice","created":"2022-12-29","cited_by_count":56,"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":"2112.03476","title":"Defending against Model Stealing via Verifying Embedded External Features","created":"2021-12-07","cited_by_count":46,"area":null},{"id":"2112.05588","title":"Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models","created":"2021-12-10","cited_by_count":46,"area":"safety"},{"id":"2201.11692","title":"SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders","created":"2022-01-27","cited_by_count":45,"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":"2405.15012","title":"Extracting Prompts by Inverting LLM Outputs","created":"2024-05-23","cited_by_count":41,"area":null},{"id":"2102.04140","title":"Quantifying and Mitigating Privacy Risks of Contrastive Learning","created":"2021-02-08","cited_by_count":36,"area":"safety"},{"id":"2209.09024","title":"Dataset Inference for Self-Supervised Models","created":"2022-09-16","cited_by_count":36,"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":"2111.07608","title":"Property Inference Attacks Against GANs","created":"2021-11-15","cited_by_count":33,"area":"safety"},{"id":"2303.03446","title":"Students Parrot Their Teachers: Membership Inference on Model Distillation","created":"2023-03-06","cited_by_count":33,"area":"safety"},{"id":"2205.06504","title":"DualCF: Efficient Model Extraction Attack from Counterfactual Explanations","created":"2022-05-13","cited_by_count":32,"area":null},{"id":"2201.07513","title":"Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders","created":"2022-01-19","cited_by_count":31,"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":"2205.14550","title":"Machine Learning for Microcontroller-Class Hardware: A Review","created":"2022-05-29","cited_by_count":28,"area":null},{"id":"2105.00623","title":"Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack","created":"2021-05-03","cited_by_count":25,"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":"2205.07890","title":"On the Difficulty of Defending Self-Supervised Learning against Model Extraction","created":"2022-05-16","cited_by_count":22,"area":null},{"id":"2201.09243","title":"Increasing the Cost of Model Extraction with Calibrated Proof of Work","created":"2022-01-23","cited_by_count":21,"area":null},{"id":"2208.02820","title":"MOVE: Effective and Harmless Ownership Verification via Embedded External Features","created":"2022-08-04","cited_by_count":21,"area":null},{"id":"2210.15427","title":"Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks","created":"2022-10-21","cited_by_count":21,"area":null},{"id":"2310.07152","title":"No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML","created":"2023-10-11","cited_by_count":21,"area":null},{"id":"2312.05386","title":"Model Extraction Attacks Revisited","created":"2023-12-08","cited_by_count":21,"area":null},{"id":"2303.09732","title":"Rethinking White-Box Watermarks on Deep Learning Models under Neural Structural Obfuscation","created":"2023-03-17","cited_by_count":20,"area":"safety"},{"id":"2412.20953","title":"GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search","created":"2024-12-30","cited_by_count":20,"area":"rag"},{"id":"2209.09841","title":"Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation","created":"2022-09-20","cited_by_count":19,"area":"distill"},{"id":"2105.12049","title":"Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs","created":"2021-05-25","cited_by_count":18,"area":null},{"id":"2302.06279","title":"Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data","created":"2023-02-13","cited_by_count":18,"area":null},{"id":"2102.07762","title":"Membership Inference Attacks are Easier on Difficult Problems","created":"2021-02-15","cited_by_count":17,"area":"safety"},{"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":"2305.06473","title":"Securing Distributed SGD against Gradient Leakage Threats","created":"2023-05-10","cited_by_count":14,"area":null},{"id":"2310.11397","title":"Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning","created":"2023-10-17","cited_by_count":14,"area":"safety"},{"id":"2402.01096","title":"Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance","created":"2024-02-02","cited_by_count":14,"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":"2407.10886","title":"SLIP: Securing LLMs IP Using Weights Decomposition","created":"2024-07-15","cited_by_count":14,"area":null},{"id":"2501.16750","title":"HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns","created":"2025-01-28","cited_by_count":14,"area":null},{"id":"2203.02777","title":"Cosine Model Watermarking Against Ensemble Distillation","created":"2022-03-05","cited_by_count":13,"area":"safety"},{"id":"2208.02878","title":"Differentially Private Counterfactuals via Functional Mechanism","created":"2022-08-04","cited_by_count":13,"area":null},{"id":"2205.10364","title":"Learning to Reverse DNNs from AI Programs Automatically","created":"2022-05-20","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":"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":"2404.11121","title":"TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment","created":"2024-04-17","cited_by_count":11,"area":null},{"id":"2411.10023","title":"Model Inversion Attacks: A Survey of Approaches and Countermeasures","created":"2024-11-15","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":"2212.05428","title":"ezDPS: An Efficient and Zero-Knowledge Machine Learning Inference Pipeline","created":"2022-12-11","cited_by_count":10,"area":null},{"id":"2502.15680","title":"Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2202.12319","title":"Privacy-preserving machine learning with tensor networks","created":"2022-02-24","cited_by_count":9,"area":null},{"id":"2207.00091","title":"Threat Assessment in Machine Learning based Systems","created":"2022-06-30","cited_by_count":9,"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":"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":"2407.01251","title":"QUEEN: Query Unlearning against Model Extraction","created":"2024-07-01","cited_by_count":9,"area":"safety"},{"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":"2310.08571","title":"Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders","created":"2023-10-12","cited_by_count":8,"area":null},{"id":"2410.11182","title":"A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality","created":"2024-10-15","cited_by_count":8,"area":null},{"id":"2502.19567","title":"Atlas: A Framework for ML Lifecycle Provenance & Transparency","created":"2025-02-26","cited_by_count":8,"area":"safety"},{"id":"2505.12442","title":"IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems","created":"2025-05-18","cited_by_count":8,"area":"agents"},{"id":"2506.02362","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","created":"2025-06-03","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":"2210.15614","title":"Private and Reliable Neural Network Inference","created":"2022-10-27","cited_by_count":7,"area":null},{"id":"2405.02365","title":"ModelShield: Adaptive and Robust Watermark against Model Extraction Attack","created":"2024-05-03","cited_by_count":7,"area":"safety"},{"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":"2204.12816","title":"The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild","created":"2022-04-27","cited_by_count":6,"area":null},{"id":"2205.00199","title":"Cracking White-box DNN Watermarks via Invariant Neuron Transforms","created":"2022-04-30","cited_by_count":6,"area":null},{"id":"2207.10561","title":"Careful What You Wish For: on the Extraction of Adversarially Trained Models","created":"2022-07-21","cited_by_count":6,"area":null},{"id":"2310.17534","title":"SoK: Pitfalls in Evaluating Black-Box Attacks","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2311.04588","title":"Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selection","created":"2023-11-08","cited_by_count":6,"area":null},{"id":"2311.11796","title":"Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems","created":"2023-11-20","cited_by_count":6,"area":"safety"},{"id":"2312.05924","title":"Data-Free Hard-Label Robustness Stealing Attack","created":"2023-12-10","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":"2405.16285","title":"ModelLock: Locking Your Model With a Spell","created":"2024-05-25","cited_by_count":6,"area":null},{"id":"2409.18214","title":"Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey","created":"2024-09-26","cited_by_count":6,"area":"diffusion"},{"id":"2410.08111","title":"Active Fourier Auditor for Estimating Distributional Properties of ML Models","created":"2024-10-10","cited_by_count":6,"area":null},{"id":"2502.16065","title":"A Survey of Model Extraction Attacks and Defenses in Distributed Computing Environments","created":"2025-02-22","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":"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":"2303.08581","title":"Model Extraction Attacks on Split Federated Learning","created":"2023-03-13","cited_by_count":5,"area":null},{"id":"2303.18132","title":"A Desynchronization-Based Countermeasure Against Side-Channel Analysis of Neural Networks","created":"2023-03-25","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":"2309.11013","title":"ModelGiF: Gradient Fields for Model Functional Distance","created":"2023-09-20","cited_by_count":5,"area":null}],"next_cursor":"100"}