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.
Apollo: A Posteriori Label-Only Membership Inference Attack Towards Machine Unlearning
When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning
Membership Inference Attacks on Sequence Models
An Out-Of-Distribution Membership Inference Attack Approach for Cross-Domain Graph Attacks
A Training Framework for Optimal and Stable Training of Polynomial Neural Networks
Securing Genomic Data Against Inference Attacks in Federated Learning Environments
AugMixCloak: A Defense against Membership Inference Attacks via Image Transformation
Automatic Calibration for Membership Inference Attack on Large Language Models
A new membership inference attack that spots memorization in generative and predictive models: Loss-Based with Reference Model algorithm (LBRM)
DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation
Graph-Level Label-Only Membership Inference Attack against Graph Neural Networks
DP-GPL: Differentially Private Graph Prompt Learning
Efficient Membership Inference Attacks by Bayesian Neural Network
Split-n-Chain: Privacy-Preserving Multi-Node Split Learning with Blockchain-Based Auditability
Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
Membership Inference Attacks for Face Images Against Fine-Tuned Latent Diffusion Models
A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attack
DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
Privacy Attacks on Image AutoRegressive Models
Tool Unlearning for Tool-Augmented LLMs
Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
Redefining Machine Unlearning: A Conformal Prediction-Motivated Approach
Differentially Private Steering for Large Language Model Alignment
Membership Inference Attacks Against Vision-Language Models
Unlearning Clients, Features and Samples in Vertical Federated Learning
Technical Report for the Forgotten-by-Design Project: Targeted Obfuscation for Machine Learning
Tag&Tab: Pretraining Data Detection in Large Language Models Using Keyword-Based Membership Inference Attack
AdaMixup: A Dynamic Defense Framework for Membership Inference Attack Mitigation
A Statistical and Multi-Perspective Revisiting of the Membership Inference Attack in Large Language Models
Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learning
Effectiveness of L2 Regularization in Privacy-Preserving Machine Learning
Membership Inference Attack against Long-Context Large Language Models
On the Privacy Risk of In-context Learning
Membership Inference Attacks against Large Vision-Language Models
TDDBench: A Benchmark for Training data detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.