Papers with Code 아카이브

Privacy Preserving Deep Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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).

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/htwang14/PA-HMDB51

공식 코드

Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset

https://github.com/huang-research-group/LDPbandit2020

공식 코드

Locally Differentially Private (Contextual) Bandits Learning

https://github.com/hyhmia/BlindMI

공식 코드

Practical Blind Membership Inference Attack via Differential Comparisons

https://github.com/iamgroot42/auditingmi

공식 코드

Do Parameters Reveal More than Loss for Membership Inference?

https://github.com/iamgroot42/iha_hild

공식 코드

Do Parameters Reveal More than Loss for Membership Inference?

https://github.com/iamgroot42/mimir

공식 코드

Do Membership Inference Attacks Work on Large Language Models?

https://github.com/iyempissy/rebMIGraph

공식 코드

Membership Inference Attack on Graph Neural Networks

https://github.com/izakariyya/idg-dp

공식 코드

Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity Recognition

https://github.com/jayoungkim408/mia

공식 코드

An Empirical Study on the Membership Inference Attack against Tabular Data Synthesis Models

https://github.com/jiangnanh/ppml-workshop

공식 코드

LTU Attacker for Membership Inference

https://github.com/jiepku/mia-safecompress

공식 코드

Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment

https://github.com/jiepku/safecompress

공식 코드

Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment

https://github.com/jinzhuoran/rwku

공식 코드

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models

https://github.com/khanhnguyen21006/mia_docvqa

공식 코드

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models

https://github.com/khoaguin/hesplitnet

공식 코드

Split Without a Leak: Reducing Privacy Leakage in Split Learning

https://github.com/kong13661/pia

공식 코드

An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization

https://github.com/kvgarimella/sisyphus-ppml

공식 코드

Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning

https://github.com/liar-mask/fedmia

공식 코드

FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning

https://github.com/lingjuanlv/FPPDL

공식 코드

Towards Fair and Privacy-Preserving Federated Deep Models

https://github.com/lions-epfl/vl-mia

공식 코드

Membership Inference Attacks against Large Vision-Language Models

https://github.com/lioutang/unlearn-apollo-attack

공식 코드

Apollo: A Posteriori Label-Only Membership Inference Attack Towards Machine Unlearning

https://github.com/liuyugeng/ml-doctor

공식 코드

ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models

https://github.com/luckyos-code/mia-covid

공식 코드

Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version)

https://github.com/machine-learning-security-lab/mia_prune

공식 코드

Membership Inference Attacks and Defenses in Neural Network Pruning

https://github.com/matlecu/adaptive_rdp

공식 코드

Practical Privacy Filters and Odometers with Rényi Differential Privacy and Applications to Differentially Private Deep Learning

https://github.com/meghdad92/scrub

공식 코드

Towards Unbounded Machine Unlearning

https://github.com/microsoft/intrinsic-private-sgd

공식 코드

An Empirical Study on the Intrinsic Privacy of SGD

https://github.com/minxingzhang/miagm

공식 코드

Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models

https://github.com/multimodalmi/multimodal-membership-inference

공식 코드

M^4I: Multi-modal Models Membership Inference

https://github.com/negedng/ma-fl-mia

공식 코드

Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning

https://github.com/ocram17/duck

공식 코드

DUCK: Distance-based Unlearning via Centroid Kinematics

https://github.com/privacytrustlab/ml_privacy_meter

공식 코드

ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learning

https://github.com/s3l-official/slmia-sr

공식 코드

SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems

https://github.com/salehzz/acmia

공식 코드

Automatic Calibration for Membership Inference Attack on Large Language Models

https://github.com/shams-sam/privacygans

공식 코드

Can we Generalize and Distribute Private Representation Learning?

https://github.com/shrezaei/MI-on-EL

공식 코드

Accuracy-Privacy Trade-off in Deep Ensemble: A Membership Inference Perspective

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.