When will CIFAR-10 adversarial robustness (L_inf) cross 80%?
Basic
6
Ṁ12252031
1D
1W
1M
ALL
3%
2023
48%
2024
35%
2025
4%
2026
3%
2027
2%
2028
2%
2029
1.5%
2030+
1.5%
Never (it is shown that this is an impossible task).
Resolved according to https://robustbench.github.io/#div_cifar10_Linf_heading. In case Robust Bench stops being active or better attacks/defenses are known which are not listed on Robust Bench, SOTA will be the resolution criteria.
The question resoves to 2030+ if it has not reached 80% for Jan 1 2031 and there is no compelling proof that this is an impossible task.
See https://bounded-regret.ghost.io/ai-forecasting-one-year-in/ for a related discussion.
I will not bet in this market.
Get
1,000
and1.00
Related questions
Related questions
Will openAI have the most accurate LLM across most benchmarks by EOY 2024?
39% chance
Will an LLM be able to match the ground truth >85% of the time when performing PII detection by 2024 end?
84% chance
Will the Jan 2024 version of the LLM detector "Binoculars" be effective against OpenAI's best model at end 2024?
59% chance
Will Gemini-1.5-Pro-Exp-0801 Score Lower Than 8 (current best) in Scale AI's
Adversarial Robustness
56% chance
Will AI image generating models score >= 90% on Winoground by June 1, 2025?
81% chance