AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection

Youheng Sun, Shengming Yuan, Xuanhan Wang, Lianli Gao, Jingkuan Song

ECCV 2024 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
condition on target images with latent infection instead of class labels, enabling unknown targetsGAKer vs HGN · Unknown classes, Res-50 -> VGG-19targeted attack success rate (%): 0.15 -> 26.02Improved
select known classes with similarity greedy algorithm (most dissimilar features) instead of random (ablation)GAKer · Res-50 -> Res-152targeted attack success rate (%): +16.52%Improved
select training images with lowest classification loss instead of random or highest loss (ablation)GAKer · unknown classes, Res-50targeted attack success rate (%)Improved
increase number of known classes to 500 (ablation)GAKer · unknown classes, Res-50targeted attack success rate (%): 49.45 white-box on 500 unknown classes at N=500No clear effect
use very few known classes (N=10 or 50) (ablation)GAKer · unknown classestargeted attack success rate (%)Hurt
use more than 325 images per known class (ablation)GAKer · unknown classes, Res-50targeted attack success rate (%): peak 41.69 at M=325Hurt
use fewer than 325 images per known class (ablation)GAKer · unknown classes, Res-50targeted attack success rate (%)Hurt
GAKer vs ESMA on known classes with Res-50 surrogateGAKer · known classes, Res-50 surrogatetargeted attack success rate (%) avg: 61.37 -> 58.71Hurt
GAKer-10 vs single-target TTP-10 with VGG-19 surrogateGAKer · known classes (10), VGG-19 surrogatetargeted attack success rate (%) avg: 36.98 -> 25.51Hurt
train one generator for all target classes instead of retraining per class batchGAKer vs TTP · training timerelative training time: 100% -> 1%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy