Andrew Ilyas
Scholar

Andrew Ilyas

Google Scholar ID: Dtw3YBoAAAAJ
Massachusetts Institute of Technology
Computer Science
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
13,684
 
H-index
29
 
i10-index
37
 
Publications
20
 
Co-authors
50
list available
Contact
CVOpen ↗GitHubOpen ↗
Publications
12 items
Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection
2026
Cited
0
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
2026
Cited
0
Data Attribution at Scale via Influence Matrix Estimation
2026
Cited
0
Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale
2026
Cited
0
Justified or Just Convincing? Error Verifiability as a Dimension of LLM Quality
2026
Cited
0
Large-Scale, Longitudinal Study of Large Language Models During the 2024 US Election Season
2025
Cited
0
Optimizing Canaries for Privacy Auditing with Metagradient Descent
2025
Cited
0
Probably Approximately Correct Labels
2025
Cited
0
Resume
Research Experience
  • Incoming Assistant Professor at Carnegie Mellon University starting Spring 2026.
  • Former Stein Fellow at Stanford Statistics.
  • Co-organized the REFORM reading group at Stanford with Amin Saberi.
  • Co-organized the ATTRIB Workshop at NeurIPS 2023 and NeurIPS 2024.
  • Delivered a tutorial on data attribution at ICML 2024 with Logan Engstrom et al.
Co-authors
15 total
Logan Engstrom
Logan Engstrom
MIT
Aleksander Mądry
Aleksander Mądry
MIT
Anish Athalye
Anish Athalye
Massachusetts Institute of Technology
Hadi Salman
Hadi Salman
OpenAI, MIT
Brandon Tran
Brandon Tran
Ph.D, MIT
Sung Min Park
Sung Min Park
Postdoc, Stanford University
Guillaume Leclerc
Guillaume Leclerc
PhD Student
Constantinos Daskalakis
Constantinos Daskalakis
Professor of Computer Science, MIT