{"total":165,"rows":[{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"id":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263,"area":"synth"},{"id":"2302.03162","title":"Protecting Language Generation Models via Invisible Watermarking","created":"2023-02-06","cited_by_count":90,"area":"safety"},{"id":"2112.02701","title":"Protecting Intellectual Property of Language Generation APIs with Lexical Watermark","created":"2021-12-05","cited_by_count":84,"area":"safety"},{"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":"2302.04460","title":"Bag of Tricks for Training Data Extraction from Language Models","created":"2023-02-09","cited_by_count":70,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"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":"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":"2107.01614","title":"Survey: Leakage and Privacy at Inference Time","created":"2021-07-04","cited_by_count":44,"area":null},{"id":"2309.05610","title":"Privacy Side Channels in Machine Learning Systems","created":"2023-09-11","cited_by_count":40,"area":null},{"id":"2106.15764","title":"The Threat of Offensive AI to Organizations","created":"2021-06-30","cited_by_count":38,"area":null},{"id":"2105.07381","title":"Undistillable: Making A Nasty Teacher That CANNOT teach students","created":"2021-05-16","cited_by_count":36,"area":"distill"},{"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":"2205.06504","title":"DualCF: Efficient Model Extraction Attack from Counterfactual Explanations","created":"2022-05-13","cited_by_count":32,"area":null},{"id":"2210.03312","title":"Distillation-Resistant Watermarking for Model Protection in NLP","created":"2022-10-07","cited_by_count":30,"area":"safety"},{"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":"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":"2207.05164","title":"Machine Learning Security in Industry: A Quantitative Survey","created":"2022-07-11","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":"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":"2304.06607","title":"False Claims against Model Ownership Resolution","created":"2023-04-13","cited_by_count":17,"area":null},{"id":"2401.15239","title":"MEA-Defender: A Robust Watermark against Model Extraction Attack","created":"2024-01-26","cited_by_count":17,"area":"safety"},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2202.10276","title":"Poisoning Attacks and Defenses on Artificial Intelligence: A Survey","created":"2022-02-21","cited_by_count":16,"area":"safety"},{"id":"2304.08566","title":"GrOVe: Ownership Verification of Graph Neural Networks using Embeddings","created":"2023-04-17","cited_by_count":16,"area":null},{"id":"2312.08890","title":"Defenses in Adversarial Machine Learning: A Survey","created":"2023-12-13","cited_by_count":14,"area":null},{"id":"2402.01096","title":"Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance","created":"2024-02-02","cited_by_count":14,"area":null},{"id":"2105.13697","title":"AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryption","created":"2021-05-28","cited_by_count":13,"area":"safety"},{"id":"2203.02777","title":"Cosine Model Watermarking Against Ensemble Distillation","created":"2022-03-05","cited_by_count":13,"area":"safety"},{"id":"2207.01991","title":"Conflicting Interactions Among Protection Mechanisms for Machine Learning Models","created":"2022-07-05","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":"2303.06280","title":"Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks","created":"2023-03-11","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":"2305.03888","title":"Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoning","created":"2023-05-06","cited_by_count":10,"area":null},{"id":"2506.17709","title":"CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition","created":"2025-06-21","cited_by_count":10,"area":null},{"id":"2204.12822","title":"A Survey on XAI for 5G and Beyond Security: Technical Aspects, Challenges and Research Directions","created":"2022-04-27","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":"2101.02069","title":"Model Extraction and Defenses on Generative Adversarial Networks","created":"2021-01-06","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":"2210.13631","title":"On the Robustness of Dataset Inference","created":"2022-10-24","cited_by_count":8,"area":null},{"id":"2302.10739","title":"MalProtect: Stateful Defense Against Adversarial Query Attacks in ML-based Malware Detection","created":"2023-02-21","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":"2403.14772","title":"Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures","created":"2024-03-21","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":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8,"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":"2405.02365","title":"ModelShield: Adaptive and Robust Watermark against Model Extraction Attack","created":"2024-05-03","cited_by_count":7,"area":"safety"},{"id":"2408.01978","title":"AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning","created":"2024-08-04","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":"2107.01806","title":"Evaluating the Cybersecurity Risk of Real World, Machine Learning Production Systems","created":"2021-07-05","cited_by_count":6,"area":null},{"id":"2110.07683","title":"Don't Knock! Rowhammer at the Backdoor of DNN Models","created":"2021-10-14","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":"2310.14047","title":"MeaeQ: Mount Model Extraction Attacks with Efficient Queries","created":"2023-10-21","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":"2411.17461","title":"SoK: Blockchain-Based Decentralized AI (DeAI)","created":"2024-11-26","cited_by_count":6,"area":null},{"id":"2501.01090","title":"HoneypotNet: Backdoor Attacks Against Model Extraction","created":"2025-01-02","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":"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":"2309.11013","title":"ModelGiF: Gradient Fields for Model Functional Distance","created":"2023-09-20","cited_by_count":5,"area":null},{"id":"2312.13435","title":"The Adaptive Arms Race: Redefining Robustness in AI Security","created":"2023-12-20","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":"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},{"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":"2210.11728","title":"Distilling the Undistillable: Learning from a Nasty Teacher","created":"2022-10-21","cited_by_count":4,"area":"distill"},{"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":"2512.09403","title":"Black-Box Behavioral Distillation Breaks Safety Alignment in Medical LLMs","created":"2025-12-10","cited_by_count":4,"area":"alignment"},{"id":"2104.02425","title":"The Duo of Artificial Intelligence and Big Data for Industry 4.0: Review of Applications, Techniques, Challenges, and Future Research Directions","created":"2021-04-06","cited_by_count":3,"area":null},{"id":"2104.12623","title":"Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Models","created":"2021-04-26","cited_by_count":3,"area":null},{"id":"2106.11424","title":"HODA: Hardness-Oriented Detection of Model Extraction Attacks","created":"2021-06-21","cited_by_count":3,"area":null},{"id":"2110.08036","title":"Generating Natural Language Adversarial Examples through An Improved Beam Search Algorithm","created":"2021-10-15","cited_by_count":3,"area":null},{"id":"2111.01080","title":"ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack","created":"2021-11-01","cited_by_count":3,"area":null},{"id":"2201.06093","title":"Adversarial Machine Learning Threat Analysis and Remediation in Open Radio Access Network (O-RAN)","created":"2022-01-16","cited_by_count":3,"area":null},{"id":"2203.10923","title":"TinyMLOps: Operational Challenges for Widespread Edge AI Adoption","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2306.00687","title":"Adversarial Robustness in Unsupervised Machine Learning: A Systematic Review","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2306.11338","title":"FDINet: Protecting against DNN Model Extraction via Feature Distortion Index","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2308.13513","title":"Unveiling the Role of Message Passing in Dual-Privacy Preservation on GNNs","created":"2023-08-25","cited_by_count":3,"area":null},{"id":"2309.01786","title":"Safe and Robust Watermark Injection with a Single OoD Image","created":"2023-09-04","cited_by_count":3,"area":null},{"id":"2312.11500","title":"A Red Teaming Framework for Securing AI in Maritime Autonomous Systems","created":"2023-12-08","cited_by_count":3,"area":"safety"},{"id":"2405.07004","title":"Stealthy Imitation: Reward-guided Environment-free Policy Stealing","created":"2024-05-11","cited_by_count":3,"area":"alignment"},{"id":"2405.12295","title":"Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks","created":"2024-05-20","cited_by_count":3,"area":null},{"id":"2411.07114","title":"TinyML Security: Exploring Vulnerabilities in Resource-Constrained Machine Learning Systems","created":"2024-11-11","cited_by_count":3,"area":null},{"id":"2411.09945","title":"TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models","created":"2024-11-15","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":"2601.15678","title":"Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems","created":"2026-01-22","cited_by_count":3,"area":"rag"},{"id":"2606.05725","title":"An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic","created":"2026-06-04","cited_by_count":3,"area":null},{"id":"2606.15810","title":"Let Them Steal: Trapping Large Language Model Extraction Attacks with Knowledge Honeypot","created":"2026-06-14","cited_by_count":3,"area":null}],"next_cursor":"100"}