Bogdan Kulynych

Graduate student at EPFL Security and Privacy Engineering Lab (SPRING). 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.

  Bogdan Kulynych, Rebekah Overdorf, Carmela Troncoso, Seda Gürses. POTs: Protective Optimization Technologies. In Fairness, Accountability, and Transparency (FAT*) Conference 2020

  Rebekah Overdorf, Bogdan Kulynych, Ero Balsa, Carmela Troncoso, Seda Gürses. Questioning the assumptions behind fairness solutions. Critiquing and Correcting Trends in Machine Learning (NeurIPS 2018 Workshop), December 7, 2018, Montreal, Canada.

  The work was used in a June 2019 US Senate testimony by Rashida Richardson.

Security and privacy in machine learning

• Towards equitable privacy protections and measurements in ML.

  Mohammad Yaghini, Bogdan Kulynych, Giovanni Cherubin, Carmela Troncoso. Disparate Vulnerability: on the Unfairness of Privacy Attacks Against Machine Learning. Privacy-Preserving Machine Learning Workshop. November, 2019, London, UK.

• Provably minimal-effort evasion attacks in constrained discrete domains.

  Bogdan Kulynych, Jamie Hayes, Nikita Samarin, Carmela Troncoso. Evading classifiers in discrete domains with provable optimality guarantees. NeurIPS 2018 Workshop on Security in Machine Learning, December 7, 2018, Montreal, Canada.

Privacy-preserving systems

• 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.

Academic service

• Reviewer at the 2021 CRAFT Track at FAccT conference.
• Co-organizer of the Participatory Approaches to ML ICML 2020 workshop
• Program committee member at the Towards Trustworthy ML ICLR 2020 workshop
• External reviewer at Privacy-Enhancing Technologies Symposium 2019–2021
• Program committee member at the Internet Science Conference Workshop on Encryption, Blockchains, and Personal Data, 2018