paper-with-me

Papers

Peak-Controlled Logits Poisoning Attack in Federated Distillation

2024-07-25 · Yuhan Tang, Aoxu Zhang, Zhiyuan Wu, Bo Gao, Tian Wen, Yuwei Wang, Sheng Sun

Federated Distillation (FD) offers an innovative approach to distributed machine learning, leveraging knowledge distillation for efficient and flexible cross-device knowledge transfer without necessitating the upload of extensive model parameters to a central server. While FD has gained popularity, its vulnerability to poisoning attacks remains underexplored. To address this gap, we previously introduced FDLA (Federated Distillation Logits Attack), a method that manipulates logits communication to mislead and degrade the performance of client models. However, the impact of FDLA on participants with different identities and the effects of malicious modifications at various stages of knowledge transfer remain unexplored. To this end, we present PCFDLA (Peak-Controlled Federated Distillation Logits Attack), an advanced and more stealthy logits poisoning attack method for FD. PCFDLA enhances the effectiveness of FDLA by carefully controlling the peak values of logits to create highly misleading yet inconspicuous modifications. Furthermore, we introduce a novel metric for better evaluating attack efficacy, demonstrating that PCFDLA maintains stealth while being significantly more disruptive to victim models compared to its predecessors. Experimental results across various datasets confirm the superior impact of PCFDLA on model accuracy, solidifying its potential threat in federated distillation systems.

📄 PDF Abstract BibTeX arXiv:2407.18039

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationTransfer Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Mitigating Evasion Attacks in Federated Learning-Based Signal Classifiers

2023-06-08 · Su Wang, Rajeev Sahay, Adam Piaseczny, Christopher G. Brinton

Recent interest in leveraging federated learning (FL) for radio signal classification (SC) tasks has shown promise but FL-based SC remains susceptible to model poisoning adversarial attacks. These adversarial attacks mis…

Adversarial AttackFederated LearningModel Poisoning

Performance Guaranteed Poisoning Attacks in Federated Learning: A Sliding Mode Approach

2025-05-22 · Huazi Pan, Yanjun Zhang, Leo Yu Zhang, Scott Adams 외

Manipulation of local training data and local updates, i.e., the poisoning attack, is the main threat arising from the collaborative nature of the federated learning (FL) paradigm. Most existing poisoning attacks aim to …

Federated LearningModel Poisoning

Logits Poisoning Attack in Federated Distillation

2024-01-08 · Yuhan Tang, Zhiyuan Wu, Bo Gao, Tian Wen 외

Federated Distillation (FD) is a novel and promising distributed machine learning paradigm, where knowledge distillation is leveraged to facilitate a more efficient and flexible cross-device knowledge transfer in federat…

Federated LearningKnowledge DistillationTransfer Learning

Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning

2025-07-01 · Wenjin Mo, Zhiyuan Li, Minghong Fang, Mingwei Fang arxiv

Federated learning (FL) allows multiple clients to collaboratively train a global machine learning model with coordination from a central server, without needing to share their raw data. This approach is particularly app…

Federated Learning

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

2026-06-08 · Bastien Vuillod, Kevin Hector, Pierre-Alain Moellic, Jean-Max Dutertre 외 arxiv

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: c…

Federated Learning