Anomaly Localization in Model Gradients Under Backdoor Attacks Against Federated Learning

Inserting a backdoor into the joint model in federated learning (FL) is a recent threat raising concerns. Existing studies mostly focus on developing effective countermeasures against this threat, assuming that backdoored local models, if any, somehow reveal themselves by anomalies in their gradients. However, this assumption needs to be elaborated by identifying specifically which gradients are more likely to indicate an anomaly to what extent under which conditions. This is an important issue given that neural network models usually have huge parametric space and consist of a large number of weights. In this study, we make a deep gradient-level analysis on the expected variations in model gradients under several backdoor attack scenarios against FL. Our main novel finding is that backdoor-induced anomalies in local model updates (weights or gradients) appear in the final layer bias weights of the malicious local models. We support and validate our findings by both theoretical and experimental analysis in various FL settings. We also investigate the impact of the number of malicious clients, learning rate, and malicious data rate on the observed anomaly. Our implementation is publicly available\footnote{\url{ https://github.com/ArcelikAcikKaynak/Federated_Learning.git}}.

Code2Image: Intelligent Code Analysis by Computer Vision Techniques and Application to Vulnerability Prediction

Intelligent code analysis has received increasing attention in parallel with the remarkable advances in the field of machine learning (ML) in recent years. A major challenge in leveraging ML for this purpose is to represent source code in a useful form that ML algorithms can accept as input. In this study, we present a novel method to represent source code as image while preserving semantic and syntactic properties, which paves the way for leveraging computer vision techniques to use for code analysis. Indeed the method makes it possible to directly enter the resulting image representation of source codes into deep learning (DL) algorithms as input without requiring any further data pre-processing or feature extraction step. We demonstrate feasibility and effectiveness of our method by realizing a vulnerability prediction use case over a public dataset containing a large number of real-world source code samples with performance evaluation in comparison to the state-of-art solutions. Our implementation is publicly available.