all AI news
A New Kind of Adversarial Example. (arXiv:2208.02430v2 [cs.CV] UPDATED)
Aug. 26, 2022, 1:11 a.m. | Ali Borji
cs.LG updates on arXiv.org arxiv.org
Almost all adversarial attacks are formulated to add an imperceptible
perturbation to an image in order to fool a model. Here, we consider the
opposite which is adversarial examples that can fool a human but not a model. A
large enough and perceptible perturbation is added to an image such that a
model maintains its original decision, whereas a human will most likely make a
mistake if forced to decide (or opt not to decide at all). Existing targeted
attacks …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US