Zico Kolter
CMU professor and head of the OpenAI Safety and Security Committee; widely cited researcher on adversarial robustness and AI safety.
- Role
- professor
- Currently at
- Carnegie Mellon University
- twitter.com/zicokolter
- Scholar
- scholar.google.com/citations
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
arXiv 2026
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
arXiv 2026
OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
arXiv 2025
Improving Alignment and Robustness with Circuit Breakers
arXiv 2024
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
arXiv 2024
Neural Network Verification with Branch-and-Bound for General Nonlinearities
arXiv 2024
Forcing Diffuse Distributions out of Language Models
arXiv 2024
Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation
arXiv 2022
Affiliations
Frequent co-authors
10from 8 papers