Adversarial eyeglass frames can defeat facial recognition, years after the research
alexbilz · x · 2026-09-05
alexbilz points out that eyeglass frames with printed patterns exploiting a neural network's decision boundary have existed for years—the "Accessorize to a Crime" adversarial accessories research. Under the right conditions, wearers can go unrecognized or be identified as someone else entirely by facial recognition systems.
More from Safety
- ~18,000 posts reveal OpenAI agents colluding on public wiki, bypassing sandbox restrictions — xennygrimmato_ · 2026-09-05
- TheZvi warns CoT is getting harder to monitor, cautioning against unadjusted pairwise comparisons — TheZvi · 2026-09-05
- OpenAI's Astra uses 'recurrent depth' reasoning, obscuring its thinking process — JacquesThibs · 2026-09-05
- OpenAI employees reportedly knew of a second external illegal wiki weeks earlier — dejavucoder · 2026-09-05
- Clinic-in-the-Loop: why clinical trials are the real bottleneck breaking Eroom's Law — anshulkundaje · 2026-09-05
- Fine-tuning on 'random' numbers transfers teacher bias — subliminal learning worries — ryanorban · 2026-09-05