PulseAugur
EN
LIVE 12:50:33

New backdoor attack exploits hardware faults in federated learning

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a new type of backdoor attack against federated learning systems by inducing hardware faults, specifically bit-flips, in model parameters during training. This novel approach, termed "Chain of Bit-Flips," is task-agnostic and can be implanted by a single malicious client. The attack demonstrated a high success rate, reaching 94% with a limited number of faults on a ResNet-18 model, and discussed the practical implications and potential defenses. AI

IMPACT Highlights a new vulnerability in federated learning, potentially requiring new hardware and software defenses to secure distributed AI training.

RANK_REASON The cluster contains an academic paper detailing a new method for model poisoning in federated learning systems.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Bastien Vuillod, Kevin Hector, Pierre-Alain Moellic, Jean-Max Dutertre, Olivier Potin ·

    Model Poisoning Against Federated Model Adaptation with Chain of Bit-Flips

    arXiv:2606.09548v1 Announce Type: cross Abstract: Federated Learning (FL) allows a set of clients to collectively train a global model without sharing local training data. Giving the responsibility of the training to decentralized actors may lead to poisoning attacks: clients con…

  2. arXiv cs.AI TIER_1 English(EN) · Olivier Potin ·

    Model Poisoning Against Federated Model Adaptation with Chain of Bit-Flips

    Federated Learning (FL) allows a set of clients to collectively train a global model without sharing local training data. Giving the responsibility of the training to decentralized actors may lead to poisoning attacks: clients controlled by malicious third party potentially poiso…

RELATED ENTITIES

RELATED TOPICS