paper-with-me

Papers

FedMID: A Data-Free Method for Using Intermediate Outputs as a Defense Mechanism Against Poisoning Attacks in Federated Learning

2024-04-18 · Sungwon Han, Hyeonho Song, Sungwon Park, Meeyoung Cha

Federated learning combines local updates from clients to produce a global model, which is susceptible to poisoning attacks. Most previous defense strategies relied on vectors derived from projections of local updates on a Euclidean space; however, these methods fail to accurately represent the functionality and structure of local models, resulting in inconsistent performance. Here, we present a new paradigm to defend against poisoning attacks in federated learning using functional mappings of local models based on intermediate outputs. Experiments show that our mechanism is robust under a broad range of computing conditions and advanced attack scenarios, enabling safer collaboration among data-sensitive participants via federated learning.

📄 PDF Abstract BibTeX arXiv:2404.11905

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Mutual Information Regularization for Vertical Federated Learning

2023-01-01 · Tianyuan Zou, Yang Liu, Ya-Qin Zhang

Vertical Federated Learning (VFL) is widely utilized in real-world applications to enable collaborative learning while protecting data privacy and safety. However, previous works show that parties without labels (passive…

Federated LearningVertical Federated Learning

Intermediate Outputs Are More Sensitive Than You Think

2024-12-01 · Tao Huang, Qingyu Huang, Jiayang Meng

The increasing reliance on deep computer vision models that process sensitive data has raised significant privacy concerns, particularly regarding the exposure of intermediate results in hidden layers. While traditional …

Adversarial AttackSensitivity

EMPURPLE: A Free Lunch for Diffusion Distillation based on the Information Bottleneck

2026-07-05 · Zilai Li, Lujia Bai arxiv

Diffusion models achieve impressive image-generation quality but remain expensive at inference time. Diffusion distillation reduces sampling steps, yet many distilled models, including SDXL-Lightning and distribution mat…

SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models

2026-02-02 · Haobo Wang, Weiqi Luo, Xiaojun Jia, Xiaochun Cao arxiv

Large vision-language models (VLMs) are vulnerable to transfer-based adversarial perturbations, enabling attackers to optimize on surrogate models and manipulate black-box VLM outputs. Prior targeted transfer attacks oft…

Testing the Limits of Jailbreaking Defenses with the Purple Problem

2024-03-20 · Taeyoun Kim, Suhas Kotha, aditi raghunathan

The rise of "jailbreak" attacks on language models has led to a flurry of defenses aimed at preventing undesirable responses. We critically examine the two stages of the defense pipeline: (i) defining what constitutes un…