NYU's Witnesses lets researchers prove what data their AI training used, no rerun needed
pratyusha_PS · x · 2026-11-07
NYU CDS assistant professor Pratyusha Sharma co-developed Witnesses, a tool that makes claims about AI training data checkable without repeating the full training run. Researchers are invited to try it on their next training run.
Related event: Witnesses Lets AI Training Claims Be Verified Without Reruns(2 posts)→
More from Safety
- Podcast: will Texas's new data center rules actually break AI? — thursdai_pod · 2026-11-07
- 'What TikTok sees' screenshot reveals an attractiveness score of 84.7 plus age and mood guesses — cyrus_zei · 2026-11-07
- OpenAI and fmf unveil framework to grade when AI jailbreaks enable serious cyber harm — OpenAI · 2026-11-07
- Beyond prompt injection: a field guide to 20 open-source AI agent security tools — MaryamMiradi · 2026-11-07
- If AI bug-finding scales linearly with compute, defense is in trouble — kuza55 · 2026-11-07
- Nigerian-American scientist Chinasa T. Okolo named to TIME100 AI list — ChinasaTOkolo · 2026-11-07