AUTOLYCUS: Exploiting Explainable Artificial Intelligence (XAI) for Model Extraction Attacks against Interpretable Models
- Abdullah Caglar Oksuz
- Anisa Halimi
- et al.
- 2024
- PETS 2024
Anisa Halimi is a research scientist in the AI Security & Data Privacy Team at IBM. Her research interests include privacy-enhancing technologies (including big data and genomic privacy), and social network analysis. She enjoys studying problems at the intersection of big data analytics and security or privacy.
She received her Ph.D. in Computer Science from Case Western Reserve University (CWRU), Cleveland, OH, in 2021. Her Ph.D. focuses on inference attacks in online social networks. During her Ph.D., she did a research internship in EPFL where she worked on genomic privacy. She received her B.Sc. and M.Sc. degrees in Computer Engineering from Epoka University, Tirane, Albania, in 2014 and 2015, respectively.