Profiles2022-2026
Nicholas Carlini
Google DeepMind
4Papers
1Last author
10Unique co-authors
2First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers4
- ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test CasesAuthor 3 of 3ICLR 2026 · 54 citations
- Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label SettingAuthor 1 of 5EUROCRYPT 2025 · 10 citations
- AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example DefensesAuthor 1 of 5ICML 2025
- Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial ExamplesAuthor 5 of 7NeurIPS 2022 · 39 citations
