Avital Shafran

Avital Shafran

PhD Student

The Hebrew University of Jerusalem

Biography

I’m a PhD student at the Hebrew University, advised by Prof. Shmuel Peleg and Prof. Gil Segev. I am interested in the security of machine learning and the intersection between machine learning and cryptography. I study the security of ML systems from an adversarial perspective, and attempt to understand the extent of different threat models. From the cryptographic perspective, I am interested in understanding the role of ML systems and tools in solving cryptographic tasks, and the use of existing cryptographic techniques for increasing the trustworthiness of ML systems.

In summer 2022 I was fortunate to visit the CleverHans lab at the Vector AI institute, and work with Prof. Nicolas Papernot on adversarial machine learning. More recently, in summer 2023 I was lucky to visit Cornell Tech and work with Prof. Tom Ristenpart on the interplay between machine learning and cryptography.

Education
  • PhD in Computer Science

    The Hebrew University of Jerusalem

  • M.Sc. in Computer Science, 2020

    The Hebrew University of Jerusalem

  • B.Sc. in Computer Engineering , 2017

    The Hebrew University of Jerusalem

Publications

(2024). Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents. preprint.

PDF Cite

(2024). Is ML-Based Cryptanalysis Inherently Limited? Simulating Cryptographic Adversaries via Gradient-Based Methods. Advances in Cryptology - CRYPTO, 2024.

PDF Cite

(2023). Beyond Labeling Oracles: What does it mean to steal ML models?. preprint.

PDF Cite

(2021). Membership inference attacks are easier on difficult problems. ICCV 2021.

PDF Cite

(2021). Crypto-Oriented Neural Architecture Design. ICASSP 2021.

PDF Cite