Abstract
Decentralized Finance (DeFi), underpinned by blockchain technology, has been beleaguered by recurrent security breaches, leading to billions of USD in annual losses. These attacks, characterized by their dynamic nature and high frequency, are however not impervious to detection and prevention. This presentation delves deep into an array of Artificial Intelligence (AI) techniques tailor-made to fortify blockchain-based applications. We will place a special emphasis on harnessing the prowess of Large Language Models (LLMs) for conducting thorough security audits on smart contracts through advanced prompt engineering. Additionally, we introduce “blockGPT”, a pioneering tool that produces intricate tracing representations of blockchain activity. This tool is designed to train an LLM from the ground up, enabling it to function as a real-time Intrusion Detection System. We demonstrate the efficacy of blockGPT in identifying potential threats, remarkably without the need for predefined rules, labeled training datasets, and boasting a batched throughput of up to 2,000 transactions per second.
Speaker
Prof. Arthur Gervais
Arthur Gervais is a distinguished computer scientist and Associate Professor of Information Security at University College London, where he leads a research group focused on blockchain security. His expertise spans smart contract security, decentralized systems, and blockchain privacy. Gervais has received numerous accolades for his contributions, including top-ranked computer security faculty status at UCL and Imperial, as well as Best Paper and Best Artifact awards. He has significantly impacted both academia and industry, with thousands of citations and six companies implementing his research.
In addition to his position at UCL, Gervais is an Affiliate Faculty at UC Berkeley and a pioneer in blockchain education. He co-instructed the first DeFi Massive Open Online Course alongside renowned experts, attracting over 4,000 students. Gervais actively engages with the blockchain community, regularly speaking at community venues, serving on various committees and advising startups to drive innovation and security in the field.