Anish Athalye

Email: aathalye@mit.edu (PGP: 086B3B32)
Blog: www.anishathalye.com
GitHub: github.com/anishathalye

Bio

I am a PhD student at MIT in the PDOS group, advised by Frans Kaashoek and Nickolai Zeldovich. In my free time, I do AI research with LabSix. I’m interested in formal verification, distributed systems, systems security, and artificial intelligence.

In the past, I’ve been an undergraduate at MIT, an intern at OpenAI, an intern at Dropbox, and an intern at Google. During undergrad, I co-founded Code for Good and helped run HackMIT.

Publications

  1. Anish Athalye. CoqIOA: A formalization of IO Automata in the Coq Proof Assistant. Master’s thesis, Massachusetts Institute of Technology, June 2017.
  2. Rahul Chatterjee, Anish Athalye, Devdatta Akhawe, Ari Juels, and Thomas Ristenpart. pASSWORD tYPOS and How to Correct Them Securely. IEEE Symposium on Security and Privacy 2016. (Distinguished Student Paper Award)

Preprints

  1. Anish Athalye*, Nicholas Carlini*, and David Wagner. Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples. arXiv:1802.00420.

  2. Anish Athalye*, Logan Engstrom*, Andrew Ilyas*, and Kevin Kwok. Synthesizing Robust Adversarial Examples. arXiv:1707.07397. Oral Presentation at NIPS MLSEC 2017 Workshop.

Projects