Papers with Code 아카이브

Reconstruction Attack

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

Facial reconstruction attack of facial manipulation models such as: Face swapping models, anonymization models, etc.

코드

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

https://github.com/Chayadon/Reconstruction_attack_on_DR

공식 코드

Investigating Privacy Leakage in Dimensionality Reduction Methods via Reconstruction Attack

https://github.com/TrustAIRLab/Conversation_Reconstruction_Attack

공식 코드

Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models

https://github.com/abdellahelmrini/decattack

공식 코드

Privacy Attacks in Decentralized Learning

https://github.com/deepmind/informed_adversary_mnist_reconstruction

공식 코드

Reconstructing Training Data with Informed Adversaries

https://github.com/duanyiyao/urvfl

공식 코드

URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning

https://github.com/dzungvpham/raifle

공식 코드

RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Adversarial Data Manipulation

https://github.com/eth-sri/tableak

공식 코드

TabLeak: Tabular Data Leakage in Federated Learning

https://github.com/iyempissy/anonymization-reconstruction-attack

공식 코드

A Review of Anonymization for Healthcare Data

https://github.com/jungyg/alsuv

공식 코드

Face Reconstruction Transfer Attack as Out-of-Distribution Generalization

https://github.com/llm-dra/dra

공식 코드

Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction

https://github.com/magnetar-iiith/pril

공식 코드

How Private Is Your RL Policy? An Inverse RL Based Analysis Framework

https://github.com/mmalekzadeh/vicious-classifiers

공식 코드

Vicious Classifiers: Assessing Inference-time Data Reconstruction Risk in Edge Computing

https://github.com/najeebjebreel/crr-analysis

공식 코드

An Examination of the Alleged Privacy Threats of Confidence-Ranked Reconstruction of Census Microdata

https://github.com/necst/timberstrike

공식 코드

TimberStrike: Dataset Reconstruction Attack Revealing Privacy Leakage in Federated Tree-Based Systems

https://github.com/terranceliu/rap-rank-reconstruction

공식 코드

Confidence-Ranked Reconstruction of Census Microdata from Published Statistics

https://github.com/tmlr-group/mc-gra

공식 코드

On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation

https://github.com/vidalt/DRAFT-DP

공식 코드

Training Set Reconstruction from Differentially Private Forests: How Effective is DP?

https://github.com/vidalt/draft

공식 코드

Trained Random Forests Completely Reveal your Dataset

https://github.com/zhangzhk0819/gnn-embedding-leaks

공식 코드

Inference Attacks Against Graph Neural Networks

https://github.com/Guang000/Awesome-Dataset-Distillation

Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation

https://github.com/JonasGeiping/breaching

When the Curious Abandon Honesty: Federated Learning Is Not Private

https://github.com/Manishpandey-0/Adversarial-reconstruction-attack-on-FL-using-LOKI

LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulation

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