Dr. Giulia Fanti, an assistant professor of Electrical and Computer Engineering at Carnegie Mellon University, sat down with Chainlink Labs to discuss her co-authored paper “SquirRL: Automating Attack Discovery on Blockchain Incentive Mechanisms with Deep Reinforcement Learning”.
She has also offered to answer questions about the paper here on the Smart Contract Research Forum for a limited time, so please don’t hesitate to ask!
This recording is the first episode of a new Chainlink Research Report series which features short presentations of exceptional working papers by blockchain scholars around the world.
In this episode, Dr. Giulia Fanti, an assistant professor of Electrical and Computer Engineering at Carnegie Mellon, discusses her paper “SquirRL: Automating Attack Analysis on Blockchain Incentive Mechanisms with Deep Reinforcement Learning.” This paper uses deep reinforcement learning to detect security flaws related to blockchain incentive mechanisms.
- Incentive mechanisms play an essential role in permissionless blockchains.
- Designing incentive-compatible mechanisms, in which expression of true preferences are utility maximizing, is challenging.
- Little is currently known about properties of incentive mechanisms currently operating on large-scale blockchains, making it difficult to test their behavior.
- Deep reinforcement learning can identify new attack strategies and replicate known strategies such as selfish mining, helping to identify and improve upon weaknesses that were previously unclear.
Dr. Giulia Fanti:
Dr. Giulia Fanti is an assistant professor of Electrical and Computer Engineering at Carnegie Mellon University. She received her Ph.D. in EECS from U.C. Berkeley and her B.S. in ECE from Olin College of Engineering. She is also an academic partner with the Chainlink Labs research team and was previously awarded a Chainlink research grant to further her work.
Her research interests and publications focus on the algorithmic foundations of blockchains, distributed systems, privacy-preserving technologies, and machine learning. Giulia is also a fellow for the World Economic Forum’s Global Future Council on Cybersecurity, and has received a best paper award at ACM Sigmetrics and an NSF Graduate Research Fellowship.
Some of Giulia’s work:
- SquirRL: Automating Attack Discovery on Blockchain Incentive Mechanisms with Deep Reinforcement Learning. C. Hou*, M.Zhou*, Y. Ji, P. Daian, F. Tramer, G. Fanti, A. Juels. [Replication Code on Github].
- The Effect of Network Topology on Credit Network Throughput. V. Sivaraman, W. Tang, S. B. Venkatakrishnan, G. Fanti, M. Alizadeh.
- Communication cost of consensus for nodes with limited memory. G. Fanti, N. Holden, Y. Peres, G. Ranade. [Replication Code on Github]
- Routing cryptocurrency with the spider network. V. Sivaraman, S. Bojja Venkatakrishnan, K. Ruan, P. Negi, L. Yang, R. Mittal, G. Fanti, M. Alizadeh. [Replication Code on Github].
- Design choices for central bank digital currency: Policy and technical considerations. S. Allen, S. Capkun, I. Eyal, G. Fanti, B. Ford, J. Grimmelmann, A. Juels, K. Kostiainen, S. Meiklejohn, A. Miller, E. Prasad, K. Wüst, and F. Zhang.
- On the Privacy Properties of GAN-generated samples. Z. Lin, V. Sekar, G. Fanti.