Stephen Casper

Graduate Student, Massachusetts Institute of Technology

Joined

September 2019

Names

Stephen Casper (Preferred)

Emails

****@college.harvard.edu (Confirmed)

****@mit.edu (Confirmed)

Personal Links

Career & Education History

Graduate Student

Massachusetts Institute of Technology (mit.edu)

2021 – Present

Undergrad student

Harvard University (harvard.edu)

2017 – 2021

Advisors, Relations & Conflicts

PhD Advisor

Dylan Hadfield-Menell

2021 – Present

Expertise

AI Governance

Present

AI Policy

Present

Machine Unlearning

Present

Sociotechnical AI Safety

Present

AI Safety

Present

Red-Teaming

Present

Publications

TamperBench: A Systematic Framework to Stress-Test LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla
- ICLR 2026 Workshop RSI ShortPaper
- Readers: Everyone
TamperBench: A Systematic Framework to Stress-Test LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla
- CAO Poster
- Readers: Everyone
TamperBench: A Systematic Framework to Stress-Test LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Nayeema Nonta, Matthew Kowal, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla
- ICLR 2026 AIWILD
- 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
Obfuscated Activations Bypass LLM Latent-Space Defenses
Luke Bailey, Alex Serrano, Abhay Sheshadri, Mikhail Seleznyov, Jordan Taylor, Erik Jenner, Jacob Hilton, Stephen Casper, Carlos Guestrin, Scott Emmons
- ICLR 2026 Poster
- Readers: Everyone
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Nayeema Nonta, Matthew Kowal, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla
- Submitted to ICLR 2026
- Readers: Everyone
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Kyle O'Brien, Stephen Casper, Quentin Gregory Anthony, Tomek Korbak, Robert Kirk, Xander Davies, Ishan Mishra, Geoffrey Irving, Yarin Gal, Stella Biderman
- ICLR 2026 Poster
- Readers: Everyone
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Kyle O'Brien, Stephen Casper, Quentin Gregory Anthony, Tomek Korbak, Robert Kirk, Xander Davies, Ishan Mishra, Geoffrey Irving, Yarin Gal, Stella Biderman
- BioSafe GenAI 2025 Oral
- Readers: Everyone
Practical Principles for AI Cost and Compute Accounting
Stephen Casper, Luke Bailey, Tim Schreier
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
Zora Che, Stephen Casper, Robert Kirk, Anirudh Satheesh, Stewart Slocum, Lev E McKinney, Rohit Gandikota, Aidan Ewart, Domenic Rosati, Zichu Wu, Zikui Cai, Bilal Chughtai, Yarin Gal, Furong Huang, Dylan Hadfield-Menell
- Accepted by TMLR
- Readers: Everyone

View all 64 publications

Co-Authors

View all 292 co-authors