Papers with Code 아카이브
Model extraction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 1
Model extraction attacks, aka model stealing attacks, are used to extract the parameters from the target model. Ideally, the adversary will be able to steal and replicate a model that will have a very similar performance to the target model.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
QUEEN: Query Unlearning against Model Extraction
Privacy Implications of Explainable AI in Data-Driven Systems
Beyond Slow Signs in High-fidelity Model Extraction
GENIE: Watermarking Graph Neural Networks for Link Prediction
Watermarking Counterfactual Explanations
DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks
Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory
Learnable Linguistic Watermarks for Tracing Model Extraction Attacks on Large Language Models
Knowledge Distillation-Based Model Extraction Attack using GAN-based Private Counterfactual Explanations
QuantumLeak: Stealing Quantum Neural Networks from Cloud-based NISQ Machines
Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data
Precise Extraction of Deep Learning Models via Side-Channel Attacks on Edge/Endpoint Devices
WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection
MEA-Defender: A Robust Watermark against Model Extraction Attack
Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Them
MEAOD: Model Extraction Attack against Object Detectors
SAME: Sample Reconstruction against Model Extraction Attacks
Model Extraction Attacks Revisited
Security and Privacy Challenges in Deep Learning Models
Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Service
Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selection
Like an Open Book? Read Neural Network Architecture with Simple Power Analysis on 32-bit Microcontrollers
Defense Against Model Extraction Attacks on Recommender Systems
Towards dialogue based, computer aided software requirements elicitation
MeaeQ: Mount Model Extraction Attacks with Efficient Queries
SCME: A Self-Contrastive Method for Data-free and Query-Limited Model Extraction Attack
Beyond Labeling Oracles: What does it mean to steal ML models?
Towards Few-Call Model Stealing via Active Self-Paced Knowledge Distillation and Diffusion-Based Image Generation
Safe and Robust Watermark Injection with a Single OoD Image
Business Process Text Sketch Automation Generation Using Large Language Model
The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning
Fault Injection and Safe-Error Attack for Extraction of Embedded Neural Network Models
Data-Free Model Extraction Attacks in the Context of Object Detection
Mercury: An Automated Remote Side-channel Attack to Nvidia Deep Learning Accelerator
Automated Data-Driven Model Extraction and Validation of Inverter Dynamics with Grid Support Function
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.