Dana Drachsler CohenView profile
Assistant Professor
Dana Drachsler Cohen is an Assistant Professor at the Faculty of Electrical and Computer Engineering, Technion, leading the SAFE lab (Secure Artificial Intelligence via Formal Methods and Engineering). Her research bridges formal methods and deep learning to establish security guarantees for AI systems. Her research focuses on leveraging formal analysis and synthesis techniques to mathematically prove the safety of deep learning models against adversarial attacks. Key interests include neural network robustness verification, program synthesis for repair, and privacy-preserving AI. The SAFE lab emphasizes practical system development that scales beyond theoretical methods while enhancing model transparency through customized verification programs. Her publication trends show consistent advancement in robustness verification techniques, evolving from pixel-level attacks to global robustness guarantees and privacy certification. Recent work integrates program synthesis with formal verification to create repair mechanisms and quantification methods with mathematical safety guarantees. Dr. Drachsler Cohen actively recruits students (PhD/MSc/BSc) for research in AI security and formal methods. She maintains significant service contributions as committee member for major conferences including PLDI, SPLASH, and POPL.







