{"total":99,"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":"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":"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":"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":"2112.15278","title":"Data-Free Knowledge Transfer: A Survey","created":"2021-12-31","cited_by_count":31,"area":"distill"},{"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":"2103.02927","title":"QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval","created":"2021-03-04","cited_by_count":22,"area":null},{"id":"2408.11071","title":"DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization","created":"2024-08-18","cited_by_count":22,"area":"diffusion"},{"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":"2401.15239","title":"MEA-Defender: A Robust Watermark against Model Extraction Attack","created":"2024-01-26","cited_by_count":17,"area":"safety"},{"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":"2101.08430","title":"Generative Zero-shot Network Quantization","created":"2021-01-21","cited_by_count":15,"area":null},{"id":"2407.10886","title":"SLIP: Securing LLMs IP Using Weights Decomposition","created":"2024-07-15","cited_by_count":14,"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":"2503.01742","title":"Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models","created":"2025-03-03","cited_by_count":11,"area":"safety"},{"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":"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":"2403.14772","title":"Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures","created":"2024-03-21","cited_by_count":8,"area":null},{"id":"2503.17198","title":"Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising","created":"2025-03-21","cited_by_count":8,"area":"safety"},{"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":"2102.11638","title":"Enhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual Interpolation","created":"2021-02-23","cited_by_count":7,"area":"distill"},{"id":"2204.00972","title":"DST: Dynamic Substitute Training for Data-free Black-box Attack","created":"2022-04-03","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":"2311.11796","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":"2402.11687","title":"Evaluating Efficacy of Model Stealing Attacks and Defenses on Quantum Neural Networks","created":"2024-02-18","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":"2503.00383","title":"Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems","created":"2025-03-01","cited_by_count":6,"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":"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":"2502.20924","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":"2510.09871","title":"CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs","created":"2025-10-10","cited_by_count":5,"area":"safety"},{"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":"2310.13822","title":"Adversarial Attacks on Fairness of Graph Neural Networks","created":"2023-10-20","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":"2106.11424","title":"HODA: Hardness-Oriented Detection of Model Extraction Attacks","created":"2021-06-21","cited_by_count":3,"area":null},{"id":"2211.06716","title":"PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud Inference","created":"2022-11-12","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":"2407.16164","title":"Representation Magnitude has a Liability to Privacy Vulnerability","created":"2024-07-23","cited_by_count":3,"area":null},{"id":"2206.07126","title":"Lazy Queries Can Reduce Variance in Zeroth-order Optimization","created":"2022-06-14","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":"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":"2310.00096","title":"Towards Few-Call Model Stealing via Active Self-Paced Knowledge Distillation and Diffusion-Based Image Generation","created":"2023-09-29","cited_by_count":2,"area":"diffusion"},{"id":"2310.10124","title":"A Comprehensive Study of Privacy Risks in Curriculum Learning","created":"2023-10-16","cited_by_count":2,"area":null},{"id":"2406.02027","title":"Inference Attacks: A Taxonomy, Survey, and Promising Directions","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2410.00059","title":"IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Method","created":"2024-09-29","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":"2607.00174","title":"Steal the Patch Size: Adversarially Manipulate Vision-Language Models","created":"2026-06-30","cited_by_count":2,"area":"mllm"},{"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":"2208.06228","title":"Unifying Gradients to Improve Real-world Robustness for Deep Networks","created":"2022-08-12","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":"2305.05293","title":"On the Limitations of Model Stealing with Uncertainty Quantification Models","created":"2023-05-09","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":"2312.15036","title":"SODA: Protecting Proprietary Information in On-Device Machine Learning Models","created":"2023-12-22","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":"2501.16671","title":"Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI","created":"2025-01-28","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":"2601.11952","title":"Decoder Gradient Shields: A Family of Provable and High-Fidelity Methods Against Gradient-Based Box-Free Watermark Removal","created":"2026-01-17","cited_by_count":1,"area":null},{"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":"2303.12397","title":"Edge Deep Learning Model Protection via Neuron Authorization","created":"2023-03-22","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":"2312.14677","title":"MEAOD: Model Extraction Attack against Object Detectors","created":"2023-12-22","cited_by_count":0,"area":null},{"id":"2401.16055","title":"Stolen Subwords: Importance of Vocabularies for Machine Translation Model Stealing","created":"2024-01-29","cited_by_count":0,"area":null},{"id":"2402.11953","title":"Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels","created":"2024-02-19","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},{"id":"2409.10643","title":"CaBaGe: Data-Free Model Extraction using ClAss BAlanced Generator Ensemble","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2501.09328","title":"Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks","created":"2025-01-16","cited_by_count":0,"area":"safety"},{"id":"2503.06188","title":"Attackers Can Do Better: Over- and Understated Factors of Model Stealing Attacks","created":"2025-03-08","cited_by_count":0,"area":null},{"id":"2505.24536","title":"CHIP: Chameleon Hash-based Irreversible Passport for Robust Deep Model Ownership Verification and Active Usage Control","created":"2025-05-30","cited_by_count":0,"area":"safety"},{"id":"2506.07590","title":"Explore the vulnerability of black-box models via diffusion models","created":"2025-06-09","cited_by_count":0,"area":"diffusion"},{"id":"2509.11159","title":"Stabilizing Data-Free Model Extraction","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2509.23594","title":"StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data","created":"2025-09-28","cited_by_count":0,"area":"synth"},{"id":"2511.04215","title":"Black-Box Guardrail Reverse-engineering Attack","created":"2025-11-06","cited_by_count":0,"area":"safety"},{"id":"2512.23948","title":"DivQAT: Enhancing Robustness of Quantized Convolutional Neural Networks against Model Extraction Attacks","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2601.01688","title":"DiMEx: Breaking the Cold Start Barrier in Data-Free Model Extraction via Latent Diffusion Priors","created":"2026-01-04","cited_by_count":0,"area":"diffusion"},{"id":"2601.17360","title":"Robust Privacy: Inference-Stage Privacy through Certified Robustness","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2606.03381","title":"AI Model Extraction Attacks: Bypassing Single-Client Assumptions in Defenses","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.11698","title":"T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking","created":"2026-06-10","cited_by_count":0,"area":"safety"},{"id":"2608.11495","title":"Defending against Model Extraction for GNNs with Model Reprogramming","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.26982","title":"JudgeStealer: Extracting LLM Judging Capabilities across Evaluation Protocols","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":null}