AI Paper Atlas

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

CamPI: Physical Adversarial Examples through Camera Power Signal Injection

Yanze Ren, Mingyuan Lv, Qinhong Jiang, Yan Jiang, Chen Yan, Xiaoyu Ji, Wenyuan Xu

CVPR 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition

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
increase CW trade-off coefficient c from 10^1 to 10^2 (ablation)CamPI white-box CW-L2 · NIPS 2017 untargeted, 7-model averageattack success rate (%): 79.1 -> 95.5 (L2 4.0 -> 7.3)Improved
increase c from 10^2 to 10^4 (ablation)CamPI white-box CW-L2 · NIPS 2017 untargeted, 7-model averageattack success rate (%): 95.5 -> 96.8 (L2 7.3 -> 14.8)No clear effect
relax L0 constraint from 1 to 256 perturbed blocks (ablation)CamPI black-box DE-L0 · VGG-19 simulationattack success rate (%): reaches 89.7% at 256 blocksImproved
move from simulation to physical injection (white-box)CamPI · 100 images, white-boxattack success rate (%): 98% -> 92%Hurt
move from simulation to physical injection (black-box)CamPI · 100 images, black-box L0=256attack success rate (%): 85% -> 82%Hurt
add Expectation over Transformation to optimizationCamPI physical attack · physical robustness to brightness, rotation, crop, contrast, noise, translationattack effectiveness (qualitative)Improved
increase attack distance via longer power cable (1 m to 10 m) (ablation)CamPI physical attack · physical cable length 1-10 minduced amplitude and ASRMixed
target affinity class pairs instead of arbitrary targetsCamPI white-box targeted · ImageNet valtargeted attack success rate (%): 80% to 100% across listed pairsImproved

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