4pm - 5pm
Thursday 25 March 2021
Vulnerability Detection in Ethereum Smart Contracts using Deep Neural Networks and Transfer Learning
Free
This event has passed
There is no need to register, just login to the Zoom call on the day.
Abstract
In this talk, we focus on the problem of vulnerability detection in Ethereum smart contracts. Smart contracts are programs that execute on top of blockchains and are often in charge of significant financial assets. At the same time, they were shown to suffer from various vulnerability classes (e.g., reentrancy or multiple send bugs), which were exploited multiple times in the real world – for instance, losses from cryptocurrency theft account for $1.9 billion in 2020. In our work, we present the first Deep Neural Network (DNN)-based vulnerability detection framework. It employs a multi-output architecture where the feature extractor learns the program semantics and each branch of the DNN captures the semantics of a specific vulnerability class. This architecture enables the detection of new vulnerability classes by simply concatenating a new classification branch to the feature extractor and training the new branch using transfer learning. Our framework can detect vulnerabilities in under 2 seconds per smart contract and yields an average F1 score of 95% across all evaluated vulnerability classes. It supports lightweight transfer learning to enable the detection of bugs from previously unseen vulnerability classes and outperforms existing vulnerability detection methods in terms of performance, coverage, and generalizability.
Speaker
Prof. Dr.-Ing. Alexandra Dmitrienko is an associate professor at the University of Wuerzburg in Germany, where she is heading the Secure Software Systems research group starting from 2018. Before that, she worked for about 10 years in renowned security institutions in Germany and in Switzerland: Ruhr-University Bochum (2008-2011), Fraunhofer Institute for Information Security in Darmstadt (2011-2015), and ETH Zurich (2016-2017). She holds a PhD degree in Security and Information Technology from TU Darmstadt (2015). Her PhD dissertation was awarded by the European Research Consortium in Informatics and Mathematics (ERCIM STM WG 2016 Award) and recognized as outstanding by Intel – she received an Intel Doctoral Student Honor Award. Over the past years, her research interests focused on various topics on secure software engineering, system security and privacy, and security and privacy of cyber-physical and distributed systems. More recently, she is focusing on secure and privacy-preserving Artificial Intelligence (AI) and on applications of AI for solving problems in security.
Visitor information
Find out how to get to the University, make your way around campus and see what you can do when you get here.