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.
GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation
Many-Shot Regurgitation (MSR) Prompting
Federated Graph Condensation with Information Bottleneck Principles
Towards Reliable Empirical Machine Unlearning Evaluation: A Game-Theoretic View
Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning
A Federated Parameter Aggregation Method for Node Classification Tasks with Different Graph Network Structures
$\nabla τ$: Gradient-based and Task-Agnostic machine Unlearning
Low-Cost Privacy-Preserving Decentralized Learning
Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
On the Impact of Uncertainty and Calibration on Likelihood-Ratio Membership Inference Attacks
Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?
Do Membership Inference Attacks Work on Large Language Models?
FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning
Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
De-identification is not always enough
Inference Attacks Against Face Recognition Model without Classification Layers
Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation
Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment
Task Contamination: Language Models May Not Be Few-Shot Anymore
Low-Cost High-Power Membership Inference Attacks
DUCK: Distance-based Unlearning via Centroid Kinematics
Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning
MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learning
Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption
Are Normalizing Flows the Key to Unlocking the Exponential Mechanism?
Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
The Paradox of Noise: An Empirical Study of Noise-Infusion Mechanisms to Improve Generalization, Stability, and Privacy in Federated Learning
Preserving Privacy in GANs Against Membership Inference Attack
Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models
Black-Box Training Data Identification in GANs via Detector Networks
A Comprehensive Study of Privacy Risks in Curriculum Learning
No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML
Mind the Gap: Federated Learning Broadens Domain Generalization in Diagnostic AI Models
SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems
Split Without a Leak: Reducing Privacy Leakage in Split Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.