Nicholas Carlini
where else to find them
website:https://nicholas.carlini.com
github:carlini
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 5 in the filters
on a stage with
- Christina Liaghationce
- Clay Shieldsonce
- David Wagneronce
all 10 in the filters
who talks about the same things
- Ram Shankar Siva Kumar9 talks
- Elie Bursztein10 talks
- Katharine Jarmul25 talks
- Rishabh Misra5 talks
- Gary Lopez4 talks
- Didier Girard13 talks
| title | conference | date |
|---|---|---|
| Crypto + ML 2 | Cryptography 10 Years Later: Obfuscation, Proof Systems, and Secure Computation Boot Camp 2025 | 2025-05-19 |
Concrete demos and limits: practical attacks on watermarking, model extraction, and fine-tuning protections, plus what cryptography could formalize. Shows… | ||
| Red Teaming AI Systems: The Path, the Prospect and the Perils | RSAC 2022 | 2022-06-06 |
Moderator:
Ram Shankar Siva Kumar, Data Cowboy, Microsoft, Harvard
Panelists:
Hyrum Anderson, Distinguished Engineer, Robust Intelligence
Nicholas Carlini… | ||
| GoLlURM! The Game of Life (limited) Unlimited-Register Machine! | !!Con 2021 | 2021-05-15 |
Claims a working GoLlURM CPU implemented entirely in Conway’s Game of Life using gliders and three instructions (INC, DEC, JUMP_IF_ZERO), builds 16 four‑bit… | ||
| Lessons Learned from Evaluating the Robustness of Defenses to Adversarial Examples | Frontiers of Deep Learning 2019 | 2019-07-15 |
Evaluation shows many published defenses fail under careful white‑box attack: of nine ICLR 2018 defenses tested, two hold up and seven are broken. Defenses… | ||
| Hidden Voice Commands | USENIX Security '16 | 2016-08-10 |
Researchers generate audio that humans hear as noise but voice systems transcribe as commands, producing both a white-box inversion that backsolves target text… | ||
| nothing matches | ||