Graduate student at EPFL Security and Privacy Engineering Lab (SPRING). Former intern at Google and CERN.
I am interested in the intersection of privacy, security, and machine learning.
Projects and publications
Protective optimization technologies
Protective optimization technologies (POTs)—a concept of developing technologies that counteract harmful optimization systems from outside.
Rebekah Overdorf, Bogdan Kulynych, Ero Balsa, Carmela Troncoso, Seda Gürses. POTs: Protective Optimization Technologies. Under submission.
Provable security and privacy for machine learning
Provably minimal-effort evasion attacks in constrained discrete domains. More details coming soon.
Power indices for machine learning models—game-theoretic tools that can be used to prove that certain features can not influence a classifier’s decision.
Bogdan Kulynych, Carmela Troncoso. Feature importance scores and lossless feature pruning using Banzhaf power indices. NIPS 2017 Symposium on Interpretable Machine Learning, December 7, 2017, Long Beach, CA, USA.
Privacy-preserving cryptographic data structures
ClaimChain–a system and data structure for decentralized privacy-preserving public key distribution. It has a working prototype, and is being tested by the Autocrypt opportunistic email encryption initiative.
Bogdan Kulynych, Wouter Lueks, Marios Isaakidis, George Danezis, and Carmela Troncoso. ClaimChain: Improving the Security and Privacy of In-band Key Distribution for Messaging. In 2018 Workshop on Privacy in the Electronic Society (WPES’18), October 15, 2018, Toronto, ON, Canada.
- External reviewer at Privacy-Enhancing Technologies Symposium 2019
- Program committee member at the Internet Science Conference Workshop on Encryption, Blockchains, and Personal Data, 2018