Papers with Code 아카이브
Privacy Preserving Deep Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 0
- 보존된 평가 기록
- 0
The goal of privacy-preserving (deep) learning is to train a model while preserving privacy of the training dataset. Typically, it is understood that the trained model should be privacy-preserving (e.g., due to the training algorithm being differentially private).
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Epsilon*: Privacy Metric for Machine Learning Models
Membership Inference Attacks on DNNs using Adversarial Perturbations
Towards More Realistic Membership Inference Attacks on Large Diffusion Models
Set-Membership Inference Attacks using Data Watermarking
Gaussian Membership Inference Privacy
Membership inference attack with relative decision boundary distance
Does Black-box Attribute Inference Attacks on Graph Neural Networks Constitute Privacy Risk?
An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
Do Backdoors Assist Membership Inference Attacks?
Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learning
Membership Inference Attack for Beluga Whales Discrimination
Active Membership Inference Attack under Local Differential Privacy in Federated Learning
Towards Unbounded Machine Unlearning
Targeted Attack on GPT-Neo for the SATML Language Model Data Extraction Challenge
Privacy-Preserving Representation Learning for Text-Attributed Networks with Simplicial Complexes
Membership Inference Attacks against Diffusion Models
AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Interpretable Models
Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging
Privacy Risk for anisotropic Langevin dynamics using relative entropy bounds
Interaction-level Membership Inference Attack Against Federated Recommender Systems
Training Differentially Private Graph Neural Networks with Random Walk Sampling
Holistic risk assessment of inference attacks in machine learning
Privacy-Preserving Collaborative Learning through Feature Extraction
Memorization of Named Entities in Fine-tuned BERT Models
Purifier: Defending Data Inference Attacks via Transforming Confidence Scores
Collaborative Training of Medical Artificial Intelligence Models with non-uniform Labels
Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version)
Privacy-preserving Deep Learning based Record Linkage
A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks Information
Review Learning: Alleviating Catastrophic Forgetting with Generative Replay without Generator
Deep Regression Unlearning
Privacy Attacks Against Biometric Models with Fewer Samples: Incorporating the Output of Multiple Models
M^4I: Multi-modal Models Membership Inference
Privacy-Preserving Deep Learning Model for Covid-19 Disease Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.