Ilia Shumailov

Researcher, Meta

Principal Researcher, AI Sequrity Company

Joined

September 2020

Names

Ilia Shumailov (Preferred)

I Shumailov

Emails

****@cl.cam.ac.uk (Confirmed)

****@cam.ac.uk (Confirmed)

****@cl.cam.ac.uk (Confirmed)

****@vectorinstitute.ai (Confirmed)

****@chch.ox.ac.uk (Confirmed)

****@cs.ox.ac.uk (Confirmed)

****@google.com (Confirmed)

****@gmail.com (Confirmed)

****@meta.com (Confirmed)

Personal Links

Career & Education History

Researcher

Meta (meta.com)

2026 – 2030

Principal Researcher

AI Sequrity Company (sequrity.ai)

2025 – 2026

Research Scientist

Google DeepMind (google.com)

2023 – 2025

Fellowship

University of Oxford (ox.ac.uk)

2022 – 2023

Fellowship

Vector Institute (vectorinstitute.ai)

2021 – 2022

PhD student

University of Cambridge (cam.ac.uk)

2017 – 2021

Advisors, Relations & Conflicts

No relations added

Expertise

Adversarial Machine Learning

2018 – 2022

Computer Security

2017 – 2022

Publications

Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias
Sierra Calanda Wyllie, Ilia Shumailov, Nicolas Papernot
- FAccT
- Readers: Everyone
Open Technical Problems in Open-Weight AI Model Risk Management
Stephen Casper, Kyle O'Brien, Shayne Longpre, Elizabeth Seger, Kevin Klyman, Rishi Bommasani, Aniruddha Nrusimha, Ilia Shumailov, Sören Mindermann, Steven Basart, Frank Rudzicz, Kellin Pelrine, Avijit Ghosh, Andrew Strait, Robert Kirk, Dan Hendrycks, Peter Henderson, J Zico Kolter, Geoffrey Irving, Yarin Gal et al. (2 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
Soft Instruction De-escalation Defense
Nils Philipp Walter, Chawin Sitawarin, Jamie Hayes, David Stutz, Ilia Shumailov
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against LLM Jailbreaks and Prompt Injections
Milad Nasr, Chawin Sitawarin, Sander V Schulhoff, Michael Ilie, Jamie Hayes, Juliette Pluto, Abhradeep Guha Thakurta, Shuang Song, Andreas Terzis, Ilia Shumailov, Harsh Chaudhari, Kai Yuanqing Xiao, Florian Tramèr, Nicholas Carlini
- Submitted to ICLR 2026
- Readers: Everyone
Exploiting Reasoning Patterns in Language Models for Indirect Targeted Poisoning
Harsh Chaudhari, Ethan Rathbun, Hanna Foerster, Jamie Hayes, Matthew Jagielski, Milad Nasr, Ilia Shumailov, Alina Oprea
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
A. Feder Cooper, Christopher A. Choquette-Choo, Miranda Bogen, Kevin Klyman, Matthew Jagielski, Katja Filippova, Ken Liu, Alexandra Chouldechova, Jamie Hayes, Yangsibo Huang, Eleni Triantafillou, Peter Kairouz, Nicole Elyse Mitchell, Niloofar Mireshghallah, Abigail Z. Jacobs, James Grimmelmann, Vitaly Shmatikov, Christopher De Sa, Ilia Shumailov, Andreas Terzis et al. (17 additional authors not shown)
- NeurIPS 2025 Position Paper Track Oral
- Readers: Everyone
Cascading Adversarial Bias from Injection to Distillation in Language Models
Harsh Chaudhari, Jamie Hayes, Matthew Jagielski, Ilia Shumailov, Milad Nasr, Alina Oprea
- DIG-BUG Long
- Readers: Everyone
Exploring the limits of strong membership inference attacks on large language models
Jamie Hayes, Ilia Shumailov, Christopher A. Choquette-Choo, Matthew Jagielski, Georgios Kaissis, Milad Nasr, Meenatchi Sundaram Muthu Selva Annamalai, Niloofar Mireshghallah, Igor Shilov, Matthieu Meeus, Yves-Alexandre de Montjoye, Katherine Lee, Franziska Boenisch, Adam Dziedzic, A. Feder Cooper
- NeurIPS 2025 poster
- Readers: Everyone
Turning Up the Dial: the Evolution of a Cybercrime Market Through Set-up, Stable, and Covid-19 Eras
Anh V. Vu, Jack Hughes, Ildiko Pete, Ben Collier, Yi Ting Chua, Ilia Shumailov, Alice Hutchings
- ACM Internet Measurement Conference (IMC'20)
- Readers: Everyone
Hardware and Software Platform Inference
Cheng Zhang, Hanna Foerster, Robert D. Mullins, Yiren Zhao, Ilia Shumailov
- ICML 2025 poster
- Readers: Everyone

View all 96 publications

Co-Authors

View all 164 co-authors