{"total":124,"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":"2407.19354","title":"The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies","created":"2024-07-28","cited_by_count":131,"area":"agents"},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116,"area":"safety"},{"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":"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":"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":"2305.12870","title":"Lion: Adversarial Distillation of Proprietary Large Language Models","created":"2023-05-22","cited_by_count":34,"area":null},{"id":"2109.03775","title":"FedZKT: Zero-Shot Knowledge Transfer towards Resource-Constrained Federated Learning with Heterogeneous On-Device Models","created":"2021-09-08","cited_by_count":31,"area":null},{"id":"2112.15278","title":"Data-Free Knowledge Transfer: A Survey","created":"2021-12-31","cited_by_count":31,"area":"distill"},{"id":"2302.14290","title":"Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation","created":"2023-02-28","cited_by_count":29,"area":"distill"},{"id":"2307.01610","title":"Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction","created":"2023-07-04","cited_by_count":29,"area":"safety"},{"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":"2501.04437","title":"Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions","created":"2025-01-08","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":"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":"2312.05386","title":"Model Extraction Attacks Revisited","created":"2023-12-08","cited_by_count":21,"area":null},{"id":"2505.01976","title":"A Survey on Privacy Risks and Protection in Large Language Models","created":"2025-05-04","cited_by_count":21,"area":"safety"},{"id":"2305.18413","title":"Learning to Learn from APIs: Black-Box Data-Free Meta-Learning","created":"2023-05-28","cited_by_count":18,"area":"distill"},{"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":"2205.11158","title":"IDEAL: Query-Efficient Data-Free Learning from Black-box Models","created":"2022-05-23","cited_by_count":16,"area":"distill"},{"id":"2205.11845","title":"CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature Sharing","created":"2022-05-24","cited_by_count":15,"area":"distill"},{"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":"2407.10886","title":"SLIP: Securing LLMs IP Using Weights Decomposition","created":"2024-07-15","cited_by_count":14,"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":"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":"2310.10483","title":"Passive Inference Attacks on Split Learning via Adversarial Regularization","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2404.13518","title":"Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion","created":"2024-04-21","cited_by_count":9,"area":"safety"},{"id":"2407.01251","title":"QUEEN: Query Unlearning against Model Extraction","created":"2024-07-01","cited_by_count":9,"area":"safety"},{"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":"2208.13648","title":"Dynamic Data-Free Knowledge Distillation by Easy-to-Hard Learning Strategy","created":"2022-08-29","cited_by_count":7,"area":"distill"},{"id":"2210.15614","title":"Private and Reliable Neural Network Inference","created":"2022-10-27","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":"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":"2309.00023","title":"Continual Learning From a Stream of APIs","created":"2023-08-31","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":"2312.05924","title":"Data-Free Hard-Label Robustness Stealing Attack","created":"2023-12-10","cited_by_count":6,"area":null},{"id":"2405.20990","title":"Locking Machine Learning Models into Hardware","created":"2024-05-31","cited_by_count":6,"area":null},{"id":"2303.08581","title":"Model Extraction Attacks on Split Federated Learning","created":"2023-03-13","cited_by_count":5,"area":null},{"id":"2306.08909","title":"Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Models","created":"2023-06-15","cited_by_count":5,"area":"distill"},{"id":"2403.07030","title":"AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation","created":"2024-03-11","cited_by_count":5,"area":"distill"},{"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":"2409.03741","title":"Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?","created":"2024-09-05","cited_by_count":5,"area":"safety"},{"id":"2502.02438","title":"Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment","created":"2025-02-04","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":"2506.07888","title":"SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmark","created":"2025-06-09","cited_by_count":5,"area":null},{"id":"2507.04119","title":"When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need","created":"2025-07-05","cited_by_count":5,"area":"distill"},{"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":"2311.14756","title":"Task-Distributionally Robust Data-Free Meta-Learning","created":"2023-11-23","cited_by_count":4,"area":null},{"id":"2312.10578","title":"SAME: Sample Reconstruction against Model Extraction Attacks","created":"2023-12-17","cited_by_count":4,"area":null},{"id":"2409.14122","title":"Efficient and Effective Model Extraction","created":"2024-09-21","cited_by_count":4,"area":null},{"id":"2507.20573","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","created":"2025-07-28","cited_by_count":4,"area":"safety"},{"id":"2510.27186","title":"Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications","created":"2025-10-31","cited_by_count":4,"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":"2306.11338","title":"FDINet: Protecting against DNN Model Extraction via Feature Distortion Index","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2405.07004","title":"Stealthy Imitation: Reward-guided Environment-free Policy Stealing","created":"2024-05-11","cited_by_count":3,"area":"alignment"},{"id":"2407.16164","title":"Representation Magnitude has a Liability to Privacy Vulnerability","created":"2024-07-23","cited_by_count":3,"area":null},{"id":"2409.06130","title":"Revisiting Black-Box Model Ownership Verification through Information Theory","created":"2024-09-10","cited_by_count":3,"area":"safety"},{"id":"2411.14516","title":"Memory Backdoor Attacks on Neural Networks","created":"2024-11-21","cited_by_count":3,"area":null},{"id":"2602.20418","title":"CITED: A Decision Boundary-Aware Signature for GNNs Towards Model Extraction Defense","created":"2026-02-23","cited_by_count":3,"area":null},{"id":"2106.08299","title":"Model Extraction and Adversarial Attacks on Neural Networks using Switching Power Information","created":"2021-06-15","cited_by_count":2,"area":null},{"id":"2211.01579","title":"Data-free Defense of Black Box Models Against Adversarial Attacks","created":"2022-11-03","cited_by_count":2,"area":null},{"id":"2211.13535","title":"DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks","created":"2022-11-24","cited_by_count":2,"area":"safety"},{"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":"2308.05127","title":"Data-Free Model Extraction Attacks in the Context of Object Detection","created":"2023-08-09","cited_by_count":2,"area":null},{"id":"2412.20768","title":"Sample Correlation for Fingerprinting Deep Face Recognition","created":"2024-12-30","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":"2506.04556","title":"BESA: Boosting Encoder Stealing Attack with Perturbation Recovery","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2109.14857","title":"First to Possess His Statistics: Data-Free Model Extraction Attack on Tabular Data","created":"2021-09-30","cited_by_count":1,"area":null},{"id":"2202.00008","title":"MEGA: Model Stealing via Collaborative Generator-Substitute Networks","created":"2022-01-31","cited_by_count":1,"area":null},{"id":"2303.07474","title":"Can Adversarial Examples Be Parsed to Reveal Victim Model Information?","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2307.12872","title":"Latent Code Augmentation Based on Stable Diffusion for Data-free Substitute Attacks","created":"2023-07-24","cited_by_count":1,"area":"diffusion"},{"id":"2309.01838","title":"Efficient Defense Against Model Stealing Attacks on Convolutional Neural Networks","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2405.16361","title":"LDPKiT: Superimposing Remote Queries for Privacy-Preserving Distillation","created":"2024-05-25","cited_by_count":1,"area":null},{"id":"2406.15476","title":"Self-Regulated Data-Free Knowledge Amalgamation for Text Classification","created":"2024-06-16","cited_by_count":1,"area":null},{"id":"2408.02140","title":"VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces","created":"2024-08-04","cited_by_count":1,"area":null},{"id":"2410.15429","title":"Efficient Model Extraction via Boundary Sampling","created":"2024-10-20","cited_by_count":1,"area":null},{"id":"2502.07011","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","created":"2025-02-10","cited_by_count":1,"area":"safety"},{"id":"2502.19502","title":"Models That Are Interpretable But Not Transparent","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2503.12497","title":"D-ADD: An Effective Plug-In for Defending Against Model Stealing","created":"2025-03-16","cited_by_count":1,"area":null},{"id":"2503.18081","title":"Model-Guardian: Protecting against Data-Free Model Stealing Using Gradient Representations and Deceptive Predictions","created":"2025-03-23","cited_by_count":1,"area":null},{"id":"2505.19364","title":"RADEP: A Resilient Adaptive Defense Framework Against Model Extraction Attacks","created":"2025-05-25","cited_by_count":1,"area":"safety"},{"id":"2508.06244","title":"Membership Inference Attack with Partial Features","created":"2025-08-08","cited_by_count":1,"area":"safety"},{"id":"2603.15481","title":"TabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins","created":"2026-03-16","cited_by_count":1,"area":"distill"},{"id":"2603.24857","title":"AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective","created":"2026-03-25","cited_by_count":1,"area":"safety"},{"id":"2605.18829","title":"Lossless Anti-Distillation Sampling","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2211.13171","title":"Query Efficient Cross-Dataset Transferable Black-Box Attack on Action Recognition","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2307.10997","title":"DREAM: Domain-free Reverse Engineering Attributes of Black-box Model","created":"2023-07-20","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":"2406.15635","title":"DataFreeShield: Defending Adversarial Attacks without Training Data","created":"2024-06-21","cited_by_count":0,"area":null},{"id":"2408.02814","title":"Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services","created":"2024-08-05","cited_by_count":0,"area":null}],"next_cursor":"100"}