paper-with-me

Papers

A Little Is Enough: Circumventing Defenses For Distributed Learning

2019-02-16 · NeurIPS 2019 12 · Moran Baruch, Gilad Baruch, Yoav Goldberg

Distributed learning is central for large-scale training of deep-learning models. However, they are exposed to a security threat in which Byzantine participants can interrupt or control the learning process. Previous attack models and their corresponding defenses assume that the rogue participants are (a) omniscient (know the data of all other participants), and (b) introduce large change to the parameters. We show that small but well-crafted changes are sufficient, leading to a novel non-omniscient attack on distributed learning that go undetected by all existing defenses. We demonstrate our attack method works not only for preventing convergence but also for repurposing of the model behavior (backdooring). We show that 20% of corrupt workers are sufficient to degrade a CIFAR10 model accuracy by 50%, as well as to introduce backdoors into MNIST and CIFAR10 models without hurting their accuracy

📄 PDF Abstract BibTeX arXiv:1902.06156

Code (4)

moranant/attacking_distributing_learning 공식 구현 pytorch
hwang595/DETOX pytorch
kkonstantinidis/ByzShield pytorch
kkonstantinidis/aspis pytorch

Similar Papers 제목 키워드 기반

On the Vulnerability of Backdoor Defenses for Federated Learning

2023-01-19 · Pei Fang, Jinghui Chen

Federated Learning (FL) is a popular distributed machine learning paradigm that enables jointly training a global model without sharing clients' data. However, its repetitive server-client communication gives room for ba…

Backdoor AttackFederated Learning

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

2018-02-01 · ICML 2018 7 · Anish Athalye, Nicholas Carlini, David Wagner

We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to def…

Adversarial AttackAdversarial Defense

Poisoning with A Pill: Circumventing Detection in Federated Learning

2024-07-22 · Hanxi Guo, Hao Wang, Tao Song, Tianhang Zheng 외

Without direct access to the client's data, federated learning (FL) is well-known for its unique strength in data privacy protection among existing distributed machine learning techniques. However, its distributive and i…

Federated Learning

Distributed Momentum for Byzantine-resilient Stochastic Gradient Descent

2021-01-01 · ICLR 2021 1 · El Mahdi El Mhamdi, Rachid Guerraoui, Sébastien Rouault

Byzantine-resilient Stochastic Gradient Descent (SGD) aims at shielding model training from Byzantine faults, be they ill-labeled training datapoints, software/hardware bugs, or malicious worker nodes in a distributed se…

Certified Defenses for Data Poisoning Attacks

2017-06-09 · NeurIPS 2017 12 · Jacob Steinhardt, Pang Wei Koh, Percy Liang

Machine learning systems trained on user-provided data are susceptible to data poisoning attacks, whereby malicious users inject false training data with the aim of corrupting the learned model. While recent work has pro…

Data Poisoning