PeopleofSuperintelligence

Researcher

Tal Malkin

Also known as Tal Geula Malkin, טל מלכין

Tal Malkin is a cryptographer at Columbia University whose work on the foundations of security extends to machine learning and AI. She studied at Bar-Ilan University, the Weizmann Institute of Science and MIT, where she earned a PhD under Shafi Goldwasser in 2000, and she joined Columbia in 2003. The International Association for Cryptologic Research named her a Fellow in 2020, and her work on defending implementations against side-channel attacks received an IACR Test-of-Time Award in 2024. In October 2024, she coauthored a watermarking scheme for open-source language models, and in 2026 her paper on adversarial noise in machine learning received a Best Paper Award at SODA. She is a professor of computer science at Columbia, where she directs the Cryptography Lab.

Born
1970
Badges

Years link to their sources.

Timeline

  1. 1993–2000

    A PhD under Shafi Goldwasser

    She graduates summa cum laude from Bar-Ilan University in 1993 with a bachelor's degree in mathematics and computer science, and earns a master's degree in computer science from the Weizmann Institute of Science in 1995 under Amir Pnueli. In 2000, she completes a PhD at MIT under Shafi Goldwasser, with the dissertation A Study of Secure Database Access and General Two-Party Computation.

  2. 2003–2009

    Assistant professor at Columbia

    After working as a research scientist at AT&T Labs through 2002, she joins Columbia University as an assistant professor of computer science in 2003. She earns tenure there in 2009.

  3. 2016–2021

    Program chair at CCS and CRYPTO

    She co-chairs the program committees of TCC 2016A, the ACM Conference on Computer and Communications Security (CCS) in 2017, and CRYPTO in 2021.

  4. 2020

    Named an IACR Fellow

    The International Association for Cryptologic Research names her a Fellow in 2020 for foundational contributions, including black-box separations, multiparty computation, and tamper resilience, and for service to the IACR.

  5. 2024

    An IACR Test-of-Time Award

    In 2024, her work on evaluating and defending implementations against side-channel attacks receives the IACR Test-of-Time Award for lasting impact on cryptographic theory and practice.

  6. October 2024

    Watermarking open-source language models

    In October 2024, she coauthors Provably Robust Watermarks for Open-Source Language Models with Miranda Christ, Sam Gunn and Mariana Raykova. The paper introduces a watermarking scheme for open-source LLMs that modifies the model's parameters, so the watermark can be detected from the model's outputs, and tests it on OPT-6.7B and OPT-1.3B.

  7. 2026

    A SODA best paper award

    Her paper Is Nasty Noise Actually Harder Than Malicious Noise?, written with Guy Blanc, Yizhi Huang and Rocco Servedio, receives a Best Paper Award at SODA in 2026. It compares two adversarial noise models for learning Boolean functions, a setting linked to data poisoning attacks on machine learning.

  8. As of October 2026

    Directing the Cryptography Lab

    She is a professor of computer science at Columbia University, where she directs the Cryptography Lab. In Spring 2026, she co-teaches the advanced course Cryptography + AI with Miranda Christ, whose 2026 PhD thesis on cryptographic watermarks for AI-generated content she co-advised.

Career

  1. Since 2003Columbia UniversityAssistant Professor of Computer Science
  2. Until 2002AT&TResearch Scientist

Education

  1. 2000Massachusetts Institute of TechnologyPhD
  2. 1995Weizmann Institute of ScienceMaster's degree
  3. 1993Bar-Ilan UniversityBachelor's degree

From the biography.

  1. 23% of people shaping AI who left a university for a company later returned to a universityIncludes Tal Malkin. We estimate that 468 of the 2,011 people shaping AI who left a university for a company (23%) later returned to a university after a median of 5 years, and 163 of 829 (20%) made the reverse round trip.
  2. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Tal Malkin. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  3. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Columbia University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  4. Nonprofit roles are 2.3 times as common in AI safetyIncludes Columbia University. We estimate where people focused on safety, alignment and evaluation work. Nonprofit roles appear for 25.1% of safety people with known affiliations, compared with 11.0% in other areas.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Tal Malkin yet. Send us a free-licensed photo.

  1. Tal Malkin - Wikipedia en.wikipedia.org. Checked 20 October 2026.
  2. Tal Malkin's Home Page cs.columbia.edu. Checked 20 October 2026.
  3. Tal Malkin, 2020 IACR Fellow iacr.org. Checked 20 October 2026.
  4. Provably Robust Watermarks for Open-Source Language Models arxiv.org. Checked 20 October 2026.
  5. Voices of CS: Yizhi Huang on Nasty Noise versus Malicious Noise cs.columbia.edu. Checked 20 October 2026.
  6. Is nasty noise actually harder than malicious noise? arxiv.org. Checked 20 October 2026.
  7. Tal Malkin simons.berkeley.edu. Checked 20 October 2026.