AI Paper Atlas

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

Learning to Learn Transferable Attack

Shuman Fang, Jie Li, Xianming Lin, Rongrong Ji

AAAI 2022 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transferable adversarial examples · 17 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
add data augmentation (ablation)LLTA · ImageNet-compatible, total success rate, RN50 surrogateattack success rate (%): 73.11 (-2.76) -> 75.87Improved
add model augmentation (ablation)LLTA · ImageNet-compatible, total success rate, RN50 surrogateattack success rate (%): 50.09 (-25.78) -> 75.87Improved
optimize decay factors rather than initialize all factors as 0.5 (ablation)LLTA · ImageNet-compatible, total success rate, RN50 surrogateattack success rate (%): 68.25 (-7.62) -> 75.87Improved
randomly alter the optimized decay factors to generate multiple models (ablation)LLTA · ImageNet-compatible, total success rate, RN50 surrogateattack success rate (%): 62.35 (-13.53) -> 75.87Improved
add meta-learning over augmented tasks (ablation)LLTA · ImageNet-compatible, total success rate, RN50 surrogateattack success rate (%): 62.20 (-13.67) -> 75.87Improved
use multiple decay factors instead of one (ablation)LLTA · ImageNet-compatible, natural models, RN50 surrogateattack success rate (%): 83.39% -> 84.83%Improved
combine LLTA with MILLTA · ImageNet-compatible, natural models, RN50 surrogateattack success rate (%): 86.67 -> 92.24Improved
use DI with LinBPLinBP · ImageNet-compatible, natural models, RN50 surrogateattack success rate (%): 79.36 -> 61.45Hurt

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