ICSE 2025
Sat 26 April - Sun 4 May 2025 Ottawa, Ontario, Canada
Sat 3 May 2025 14:20 - 14:40 at 204 - Paper Session 2 Chair(s): Ziyang Ye

Federated Learning (FL) is a decentralized machine learning approach that enables collaborative training among distributed clients while preserving data privacy, making it increasingly popular for privacy-sensitive applications over traditional centralized models. However, it introduces new security vulnerabilities that challenge conventional approaches to software vulnerability management. Among these, label flipping attacks (LFAs)—where malicious clients intentionally mislabel data—pose a unique threat to the integrity of FL models. This study presents an AI-driven, edge-based vulnerability detection technique, leveraging explainable AI (XAI) techniques to enhance edge-based security within FL environments. Our method combines Grad-CAM visualizations with DBSCAN clustering to analyze class-specific behavior across clients. By detecting anomalies in Grad-CAM activation patterns, we identify malicious clients with flipped class labels, exploiting patterns in their Grad-CAM heatmaps. This approach is particularly robust against LFAs, examining each class independently and capturing patterns without relying on global model behavior. Empirical results on benchmark datasets such as MNIST and FashionMNIST demonstrate that our method accurately detects LFAs, even when malicious clients constitute a substantial portion of the network. This class-specific, XAI-driven approach contributes to the security of FL by offering an explainable, and scalable solution for managing vulnerabilities in distributed AI systems.

Sat 3 May

Displayed time zone: Eastern Time (US & Canada) change

14:00 - 15:30
Paper Session 2SVM at 204
Chair(s): Ziyang Ye The University of Adelaide
14:00
20m
Talk
An Exploratory Study of Security Vulnerabilities in Machine Learning Deployment Projects
SVM
Akond Rahman Auburn University, USA, Anthony Skjellum Tennessee Tech University, Yue Zhang Auburn University
14:20
20m
Talk
Edge-Based Detection of Label Flipping Attacks in Federated Learning Using Explainable AI
SVM
Nourah Alotaibi KFUPM, Muhamad Felemban KFUPM, Sajjad Mahmood King Fahd University of Petroleum & Minerals
14:40
20m
Talk
"Just Use Rust": A Best-Case Historical Study of Open Source Vulnerabilities in C
SVM
Andy Meneely Rochester Institute of Technology, Aiden Green Rochester Institute of Technology, Tyler Jaafari Rochester Institute of Technology, Matthew Fluet Rochester Institute of Technology, Brandon Keller Rochester Institute of Technology
15:00
20m
Talk
Understanding the Changing Landscape of Automotive Software Vulnerabilities: Insights from a Seven-Year Analysis
SVM
Srijita Basu Chalmers University of Technology and University of Gothenburg, Miroslaw Staron Chalmers University of Technology and University of Gothenburg
15:20
10m
Day closing
Workshop Closing
SVM