Re:Adversarial image attacks are no joke
by siboehm on Monday November 29, 2021 @11:32AM
(#29381779)
This has always confused me as well. What would be the reason why some adversary would choose to craft an adversarial example and deploy it in the real world versus the much easier solution to just remove / obscure the sign?
[ Parent
| on HN ]
Re:Adversarial image attacks are no joke
by tonyarkles on Monday November 29, 2021 @11:38AM
(#29381872)
Depending on how big or small it needs to be, potentially for subtlety? Especially on current roads that are shared by humans and self-driving systems, a human observer will immediately notice that something is terribly wrong with a replaced sign.
But... around here at least, signs have stickers or graffiti on them often enough. Like adding the name of a politician under a stop sign: "Stop [Harper]". An appropriately made adversarial example won't stick out visually the same way that a wholesale sign swap will.