{"total":233,"rows":[{"id":"2111.06420","title":"Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities","created":"2021-11-11","cited_by_count":125,"area":null},{"id":"2205.13383","title":"BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning","created":"2022-05-26","cited_by_count":86,"area":null},{"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":"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":"2204.11022","title":"Towards Data-Free Model Stealing in a Hard Label Setting","created":"2022-04-23","cited_by_count":58,"area":null},{"id":"2205.06900","title":"MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic","created":"2022-05-13","cited_by_count":55,"area":null},{"id":"2103.10013","title":"Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!","created":"2021-03-18","cited_by_count":53,"area":null},{"id":"2212.10986","title":"SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning","created":"2022-12-21","cited_by_count":51,"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":"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":"2109.01165","title":"Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction","created":"2021-09-01","cited_by_count":37,"area":null},{"id":"2305.12870","title":"Lion: Adversarial Distillation of Proprietary Large Language Models","created":"2023-05-22","cited_by_count":34,"area":null},{"id":"2106.08890","title":"ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection","created":"2021-06-11","cited_by_count":33,"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":"2209.10117","title":"A Comprehensive Survey on Trustworthy Recommender Systems","created":"2022-09-21","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":"2510.09263","title":"SynthID-Image: Image watermarking at internet scale","created":"2025-10-10","cited_by_count":31,"area":null},{"id":"2104.12378","title":"Delving into Data: Effectively Substitute Training for Black-box Attack","created":"2021-04-26","cited_by_count":27,"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":"2110.11024","title":"Watermarking Graph Neural Networks based on Backdoor Attacks","created":"2021-10-21","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":"2206.14157","title":"How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection","created":"2022-06-28","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":"2108.09454","title":"\"Adversarial Examples\" for Proof-of-Learning","created":"2021-08-21","cited_by_count":20,"area":null},{"id":"2303.04729","title":"Stealing the Decoding Algorithms of Language Models","created":"2023-03-08","cited_by_count":19,"area":null},{"id":"2108.13873","title":"Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs","created":"2021-08-29","cited_by_count":18,"area":null},{"id":"2304.06607","title":"False Claims against Model Ownership Resolution","created":"2023-04-13","cited_by_count":17,"area":null},{"id":"2309.10058","title":"Dual Student Networks for Data-Free Model Stealing","created":"2023-09-18","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":"2208.10134","title":"Machine Learning with Confidential Computing: A Systematization of Knowledge","created":"2022-08-22","cited_by_count":15,"area":null},{"id":"2301.04006","title":"IronForge: An Open, Secure, Fair, Decentralized Federated Learning","created":"2023-01-07","cited_by_count":15,"area":null},{"id":"2502.00706","title":"Model Provenance Testing for Large Language Models","created":"2025-02-02","cited_by_count":15,"area":null},{"id":"2105.01281","title":"Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGX","created":"2021-05-04","cited_by_count":14,"area":null},{"id":"2111.04394","title":"Get a Model! Model Hijacking Attack Against Machine Learning Models","created":"2021-11-08","cited_by_count":14,"area":null},{"id":"2112.06658","title":"Learning to Learn Transferable Attack","created":"2021-12-10","cited_by_count":13,"area":null},{"id":"2204.12281","title":"Data-Efficient Backdoor Attacks","created":"2022-04-22","cited_by_count":13,"area":null},{"id":"2405.03636","title":"The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape","created":"2024-05-06","cited_by_count":13,"area":null},{"id":"2202.12506","title":"On the Effectiveness of Dataset Watermarking in Adversarial Settings","created":"2022-02-25","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":"2211.14952","title":"Federated Learning Attacks and Defenses: A Survey","created":"2022-11-27","cited_by_count":12,"area":null},{"id":"2403.01472","title":"WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection","created":"2024-03-03","cited_by_count":12,"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":"2405.11034","title":"Safety in Graph Machine Learning: Threats and Safeguards","created":"2024-05-17","cited_by_count":11,"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":"2104.05921","title":"Thief, Beware of What Get You There: Towards Understanding Model Extraction Attack","created":"2021-04-13","cited_by_count":9,"area":null},{"id":"2108.13952","title":"Morphence: Moving Target Defense Against Adversarial Examples","created":"2021-08-31","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":"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":"2101.02069","title":"Model Extraction and Defenses on Generative Adversarial Networks","created":"2021-01-06","cited_by_count":8,"area":null},{"id":"2105.10909","title":"Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs","created":"2021-05-23","cited_by_count":8,"area":null},{"id":"2107.05166","title":"Stateful Detection of Model Extraction Attacks","created":"2021-07-12","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":"2210.13631","title":"On the Robustness of Dataset Inference","created":"2022-10-24","cited_by_count":8,"area":null},{"id":"2310.06511","title":"Self-Supervised Dataset Distillation for Transfer Learning","created":"2023-10-10","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":"2506.02362","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2110.06018","title":"On the Security Risks of AutoML","created":"2021-10-12","cited_by_count":7,"area":null},{"id":"2112.00725","title":"The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image","created":"2021-12-01","cited_by_count":7,"area":null},{"id":"2210.01075","title":"Decompiling x86 Deep Neural Network Executables","created":"2022-10-03","cited_by_count":7,"area":null},{"id":"2303.18178","title":"Robust and IP-Protecting Vertical Federated Learning against Unexpected Quitting of Parties","created":"2023-03-28","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":"2408.13161","title":"Say No to Freeloader: Protecting Intellectual Property of Your Deep Model","created":"2024-08-23","cited_by_count":7,"area":null},{"id":"2409.04459","title":"WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks","created":"2024-08-29","cited_by_count":7,"area":null},{"id":"2412.08897","title":"Neural Interactive Proofs","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2106.10147","title":"Evaluating the Robustness of Trigger Set-Based Watermarks Embedded in Deep Neural Networks","created":"2021-06-18","cited_by_count":6,"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":"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":"2209.08443","title":"HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2309.00023","title":"Continual Learning From a Stream of APIs","created":"2023-08-31","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":"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":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2312.05924","title":"Data-Free Hard-Label Robustness Stealing Attack","created":"2023-12-10","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":"2204.09852","title":"The Risks of Machine Learning Systems","created":"2022-04-21","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":"2302.13570","title":"Physical Adversarial Attacks on Deep Neural Networks for Traffic Sign Recognition: A Feasibility Study","created":"2023-02-27","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":"2308.16703","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},{"id":"2406.18540","title":"Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing","created":"2024-05-18","cited_by_count":5,"area":null},{"id":"2410.13903","title":"CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2502.20924","title":"Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2602.20419","title":"CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks","created":"2026-02-23","cited_by_count":5,"area":null},{"id":"2105.06300","title":"Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey","created":"2021-05-13","cited_by_count":4,"area":null}],"next_cursor":"100"}