Can AI spot fake cosmetics? I tested Gemini on counterfeit Rhode lip tints
Identifying fake cosmetics using AI
Counterfeit cosmetics are rampant on marketplaces like eBay and TikTok Shop, and fakes can contain harmful contaminants. A lab researcher tested whether Google Gemini could identify counterfeit Rhode Peptide Lip Tint packages by analyzing photos. Gemini correctly flagged two fakes and one authentic product, catching subtle typos and cross-package inconsistencies, but also made mistakes by misinterpreting glare as printing errors and hallucinating details. The experiment suggests AI could help consumers verify authenticity, but human oversight is still needed.
Gemini’s not just looking for inconsistencies within photos; it’s also looking for inconsistencies across photos. I’ll admit that I missed this one.
- fwipsy
Replacement laptop batteries and power adapters have a huge problem with counterfeiting as well. In most cases it's a lot easier to spot because e.g. they rearrange the logos.
Even if these techniques did not produce false positives on genuine products, I suspect that they would not scale well. If counterfeiters realized they were losing a lot of sales through AI detection, they will just use AI to catch the errors themselves.
- olwmc
This guy's lab does some really cool stuff using really basic ideas:
- https://groverlab.org/research/2022-05-06-candycodes.html
- https://groverlab.org/research/2026-03-19-disintegration-fin...
(edit: Formatting)
- hn_throwaway_99
> In conclusion, I’m pretty negative about AI in general, but this experience made me cautiously optimistic about the role the technology could play in protecting consumers from counterfeit products.
Whaaaattt? How could the author go through such detail and discover that Gemini completely failed in the assigned task (calling all the products fakes when some were and some weren't means that it provided zero correct assistance in this discrimination task) and then conclude "AI could play a helpful role"??? Does the author also conclude that stopped clocks could play a helpful role telling time because the are correct twice a day?
Apparently AI isn't the only thing that hallucinates.