Scholar
Ivan Evtimov
Google Scholar ID: F0yiLRIAAAAJ
AI at Meta
Citations & Impact
Citations
17,270
H-index
17
i10-index
23
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Received Distinguished Paper Award at the Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems for work on multimodal models
- Research covered by Ars Technica, IEEE Spectrum, and others
- Published 'FoggySight: A Scheme for Facial Lookup Privacy' in Proceedings on Privacy Enhancing Technologies (PoPETs), 2021(3)
- Paper 'Disrupting Model Training with Adversarial Shortcuts' accepted to an ICML workshop
- Multiple works released as arXiv preprints (e.g., arXiv:2011.12902, arXiv:2012.08588)
Background
- Computer Science Researcher specializing in security and privacy
- Focuses on the intersection of security and machine learning
- Investigates whether adversarial examples pose real threats to deployed systems
- Advocates for a systems-wide approach to securing AI-integrated systems
- Actively explores legal and policy implications of adversarial capabilities; co-authored work through the Tech Policy Lab
Co-authors