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.
CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition
Navigating the Deep: Signature Extraction on Deep Neural Networks
Explore the vulnerability of black-box models via diffusion models
GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors
MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models
Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning
On the interplay of Explainability, Privacy and Predictive Performance with Explanation-assisted Model Extraction
Better Decisions through the Right Causal World Model
CopyQNN: Quantum Neural Network Extraction Attack under Varying Quantum Noise
ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks
ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction
A Survey of Model Extraction Attacks and Defenses in Distributed Computing Environments
Differentially private fine-tuned NF-Net to predict GI cancer type
From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks
A Framework for Double-Blind Federated Adaptation of Foundation Models
Safety at Scale: A Comprehensive Survey of Large Model Safety
Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI
"FRAME: Forward Recursive Adaptive Model Extraction -- A Technique for Advance Feature Selection"
Neural Honeytrace: A Robust Plug-and-Play Watermarking Framework against Model Extraction Attacks
HoneypotNet: Backdoor Attacks Against Model Extraction
Bounding-box Watermarking: Defense against Model Extraction Attacks on Object Detectors
Few-shot Model Extraction Attacks against Sequential Recommender Systems
A Hard-Label Cryptanalytic Extraction of Non-Fully Connected Deep Neural Networks using Side-Channel Attacks
Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
Robust and Minimally Invasive Watermarking for EaaS
Efficient Model Extraction via Boundary Sampling
Efficient and Effective Model Extraction
CaBaGe: Data-Free Model Extraction using ClAss BAlanced Generator Ensemble
Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced Distillation
VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces
Enhancing TinyML Security: Study of Adversarial Attack Transferability
QUEEN: Query Unlearning against Model Extraction
Privacy Implications of Explainable AI in Data-Driven Systems
Beyond Slow Signs in High-fidelity Model Extraction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.