7.5 KiB

Raw Blame History

Attacks in FL

Here we present recent works on the attacks in FL.

|Survey|Privacy Attacks|Backdoor Attacks|Untargeted Attacks|

Survey

Title	Venue	Link	Year
A Survey on Gradient Inversion: Attacks, Defenses and Future Directions	arxiv	pdf	2022
Threats to Federated Learning: A Survey	arxiv	pdf	2020

Privacy Attacks in FL

2022

Title	Venue	Link
Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models	ICLR	pdf
Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification	Arxiv	pdf
Bayesian Framework for Gradient Leakage	pdf
Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage	CVPR	pdf

2021

Title	Venue	Link
See through gradients: Image batch recovery via gradinversion	CVPR	pdf
Gradient disaggregation: Breaking privacy in federated learning by reconstructing the user participant matrix	ICML	pdf
Evaluating gradient inversion attacks and defenses in federated learning	NeurIPS	pdf
Bayesian framework for gradient leakage	ICLR	pdf
Catastrophic data leakage in vertical federated learning.	NeurIPS	pdf
Gradient inversion with generative image prior	NeurIPS	pdf
R-gap: Recursive gradient attack on privacy	ICLR	pdf
Understanding training-data leakage from gradients in neural networks for image classifications.	NeurIPS workshop	pdf
Soteria: Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective	CVPR	pdf
Reconstruction Attack on Instance Encoding for Language Understanding	EMNLP	pdf
Source Inference Attacks in Federated Learning	ICDM	pdf
TAG: Gradient Attack on Transformer-based Language Models	EMNLP(findings)	pdf
Unleashing the Tiger: Inference Attacks on Split Learning	CCS	pdf

2020

Title	Venue	Link
idlg: Improved deep leakage from gradients	arxiv	pdf
A framework for evaluating client privacy leakages in federated learning	ESORICS	pdf
Inverting gradients – how easy is it to break privacy in federated learning?	NeurIPS	pdf
Sapag: A self adaptive privacy attack from gradients	arxiv	pdf
Is Private Learning Possible with Instance Encoding?	S&P	pdf

2019

Title	Venue	Link
Deep Leakage from Gradients	NeurIPS	pdf
Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning	Infocom	pdf
Exploiting Unintended Feature Leakage in Collaborative Learning	S&P	pdf
Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning	S&P	pdf

2017

Title	Venue	Link
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning	CCS	pdf

Backdoor Attacks in FL

2022

Title	Venue	Link
Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information	arxiv	pdf
Neurotoxin: Durable Backdoors in Federated Learning	arxiv	pdf

2021

Title	Venue	Link
WaNet - Imperceptible Warping-based Backdoor Attack	ICLR	pdf

2020

Title	Venue	Link
Attack of the Tails: Yes, You Really Can Backdoor Federated Learning	NeurIPS	pdf
DBA: Distributed Backdoor Attacks against Federated Learning	ICLR	pdf
How To Backdoor Federated Learning	AISTATS	pdf

2019

Title	Venue	Link
BadNets: Evaluating Backdooring Attacks on Deep Neural Networks	IEEE Access	pdf
Analyzing Federated Learning through an Adversarial Lens	NeurIPS	pdf

2017

Title	Venue	Link
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning	arxiv	pdf

Untargeted Attacks in FL

2022

Title	Venue	Link
Learning to Attack Federated Learning: A Model-based Reinforcement Learning Attack Framework	NeurIPS	pdf
Poisoning Deep Learning Based Recommender Model in Federated Learning Scenarios	IJCAI	pdf

2021

Title	Venue	Link
Manipulating the byzantine: Optimizing model poisoning attacks and defenses for federated learning	NDSS	pdf

2020

Title	Venue	Link
Local Model Poisoning Attacks to Byzantine-Robust Federated Learning	USENIX SCEURITY	pdf
Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation	UAI	pdf