atlas

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

Can You Spot the Chameleon? Adversarially Camouflaging Images From Co-Salient Object Detection

CVPR 2022 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 18 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use Jadena augment instead of MI-FGSM_BCECo-saliency attack on GCAGC · Cosal2015S: 0.3975 -> 0.5146Helped
Use Jadena augment instead of ColorFoolCo-saliency attack on CBCD · Cosal2015S: 0.9663 -> 0.9816Helped
Use Jadena augment instead of MI-FGSM_BCECo-saliency attack on PoolNet · Cosal2015S: 0.3375 -> 0.6010Helped
Use Jadena augment instead of I-FGSM_BCECo-saliency attack on GICD · Cosal2015S: 0.7285 -> 0.6893Hurt
Add augmented reference images (ablation)Jadena attack on GICD · Cosal2015S: 0.6864 -> 0.6893No clear effect
Use augmented references instead of same-group references (ablation)Jadena attack on GICD · Cosal2015S: 0.6849 -> 0.6893No clear effect
Add additive noise (ablation)Jadena augment attack on GICD · Cosal2015S: 0.3226 -> 0.6893Helped
Add exposure tuning (ablation)Jadena augment attack on GICD · Cosal2015S: 0.5261 -> 0.6893Helped

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