AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Adversarial Examples for Semantic Segmentation and Object Detection

Cihang Xie, Jianyu Wang, Zhishuai Zhang, Yuyin Zhou, Lingxi Xie, Alan Yuille

ICCV 2017 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 994 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
keep the spatial structure of the perturbation instead of randomly permuting it (ablation)DAG on FR-ZF-07 · PascalVOC-2007 testmAP: 58.33 -> 3.61Improved
keep the spatial structure of the perturbation instead of randomly permuting it (ablation)DAG on FCN-VGG · VOC segmentation (736 val images)mIoU: 65.47 -> 4.09Improved
keep the spatial structure of the perturbation instead of randomly permuting it (ablation)DAG on FR-VGG-0712 · PascalVOC-2007 testmAP: 71.97 -> 3.36Improved
use a denser proposal set (higher NMS IOU rate, chosen 0.90) (ablation)DAG on FR-ZF-07 · PascalVOC-2007 testmAPImproved
train the victim detector on more data (VOC07+12 instead of VOC07)DAG attack on FR-ZF · PascalVOC-2007 testmAP: 58.70 -> 3.61 vs 61.07 -> 1.95Hurt
transfer perturbation across training sets (FR-ZF-07 to FR-ZF-0712)DAG perturbation · PascalVOC-2007 testmAP: 61.07 -> 22.15Improved
transfer perturbation across architectures (FR-ZF-07 to FR-VGG-07)DAG perturbation · PascalVOC-2007 testmAP: 69.14 -> 66.01No clear effect
transfer perturbation to black-box R-FCN-RN101 from FR-ZF-07DAG perturbation · PascalVOC-2007 test (black-box)mAP: 78.06 -> 75.87No clear effect
attack DL-VGG with FCN-VGG perturbation (same VGG backbone)DAG perturbation · VOC segmentation (736 val images, transfer)mIoU: 70.72 -> 45.16Improved
cross-task attack with same architecture: FR-VGG-07 perturbation on FCN-VGGDAG perturbation · VOC2012 seg val subset (687 images, cross-task)mIoU: 54.87 -> 43.06Improved
add FR-VGG-0712 perturbation to FR-ZF-0712 perturbation (r2+r4)DAG perturbation · PascalVOC-2007 testmAP: 68.17 -> 4.28Improved
combine r1+r3+r5+r7 instead of r1 alone for black-box attackDAG perturbation on R-FCN-RN101 · VOC2012 seg val subset (110 images, black-box)mAP: 76.00 -> 64.52Improved

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