Tsachi Blau

Tsachi Blau

Machine Learning and AI Researcher,

Ph.D. Candidate in Computer Science,

Technion – Israel Institute of Technology

I am a Ph.D. candidate in the Computer Science Department at the Technion – Israel Institute of Technology, advised by professors Alex M. Bronstein and Chaim Baskin. My research primarily focuses on adversarial attacks, robustification techniques, and generative models. I explore adversarial defense strategies using generative approaches and investigate how adversarial methodologies can enhance robustness across various applications, including natural language processing (NLP). My goal is to deepen the understanding of adversarial phenomena and contribute to advancements in machine learning and artificial intelligence.

Prior to my Ph.D. studies I completed my Master’s degree in Electrical and Computer Engineering at the Technion, advised by professors Michael Elad, Alex M. Bronstein and Chaim Baskin. I gained experience in R&D at Applied Materials, and later worked as a research intern at Amazon. I also hold a Bachelor’s degree in Electrical and Computer Engineering from the Technion.

Publications

Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods

Tsachi Blau, Moshe Kimhi, Yonatan Belinkov, Alex M. Bronstein and Chaim Baskin

Preprint, arXiv:2410.17222.

Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency

Maor Dikter, Tsachi Blau and Chaim Baskin

WACV 2025, in The IEEE/CVF Winter Conference on Applications of Computer Vision.

GRAM: Global Reasoning for Multi-Page VQA

Tsachi Blau, Sharon Fogel, Roi Ronen, Alona Golts, Roy Ganz, Elad Ben Avraham, Aviad Aberdam, Shahar Tsiper and Ron Litman

CVPR 2024, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Class-Conditioned Transformation for Enhanced Robust Image Classification

Tsachi Blau, Roy Ganz, Chaim Baskin, Michael Elad and Alex M. Bronstein

ICML 2023, in the 40th International Conference on Machine Learning Workshow on Adversarial Machine Learning.

WACV 2025, in The IEEE/CVF Winter Conference on Applications of Computer Vision.

Threat Model-Agnostic Adversarial Defense Using Diffusion Models

Tsachi Blau, Roy Ganz, Bahjat Kawar, Alex M. Bronstein and Michael Elad

Preprint, arXiv:2207.08089.