model extraction

Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks AAAI 2026 On Stealing Graph Neural Network Models AAAI 2026 A Framework for Double-Blind Federated Adaptation of Foundation Models ICCV 2025 Can Watermarks be Used to Detect LLM IP Infringement For Free? ICLR 2025 CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition ICML 2025 HoneypotNet: Backdoor Attacks Against Model Extraction AAAI 2025 Sim4Rec: Data-Free Model Extraction Attack on Sequential Recommendation AAAI 2025 StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data ICCV 2025 “Yes, My LoRD.” Guiding Language Model Extraction with Locality Reinforced Distillation ACL 2025 Beyond Slow Signs in High-fidelity Model Extraction NeurIPS 2024 Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models ACL 2024 Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing CVPR 2024 MatFormer: Nested Transformer for Elastic Inference NeurIPS 2024 Protecting Object Detection Models from Model Extraction Attack via Feature Space Coverage IJCAI 2024 Training A Secure Model against Data-Free Model Extraction ECCV 2024 WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection ACL 2024 An Exact Poly-Time Membership-Queries Algorithm for Extracting a Three-Layer ReLU Network ICLR 2023 DisGUIDE: Disagreement-Guided Data-Free Model Extraction AAAI 2023 Dual Student Networks for Data-Free Model Stealing ICLR 2023 Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack NeurIPS 2023 MeaeQ: Mount Model Extraction Attacks with Efficient Queries EMNLP 2023 Protecting Language Generation Models via Invisible Watermarking ICML 2023 Extracted BERT Model Leaks More Information than You Think! EMNLP 2022 Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations CVPR 2022 Increasing the Cost of Model Extraction with Calibrated Proof of Work ICLR 2022