Bogdan Kulynych

Evading classifiers in discrete domains with provable optimality guarantees

2018 · arXiv (Cornell University)

Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from having provable guarantees against adversarial examples. The existing literature on provable adversarial robustness …

Arbitrary Decisions are a Hidden Cost of Differentially Private Training

2023

Mechanisms used in privacy-preserving machine learning often aim to guarantee differential privacy (DP) during model training. Practical DP-ensuring training methods use randomization when fitting model parameters to privacy-sensitive data (e.g., adding Gaussian noise to clipped …