AI Paper Atlas

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

Global-Local Characteristic Excited Cross-Modal Attacks from Images to Videos

Ruikui Wang, Yuanfang Guo, Yunhong Wang

AAAI 2023 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transferable adversarial examples · 10 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 global inter-frame interaction enhancement (GIE) (ablation)I2V-style cross-modal video attacks · UCF-101 and Kinetics-400Average ASR (%): improved by 2.2% ∼8.5% and 1.5% ∼9.6%Improved
Add local correlation disturbance (LCD) (ablation)I2V-style cross-modal video attacks · UCF-101 and Kinetics-400Average ASR (%): 6.1%Mixed
Combine GIE and LCD (ablation)I2V baseline · UCF-101 and Kinetics-400Average ASR (%): 6.5% ∼10.1% and 3.8% ∼13.6%Improved
Use GIE with n1=2 and n2=3 rather than the baseline (ablation)VGG-16 substitute-model attack · UCF-101 and Kinetics-400Average ASR (%): 36.63 -> 44.06; 56.42 -> 66.04Improved
Increase the number of GIE interaction combinations from n2=2 to n2=3 with n1=2 (ablation)VGG-16 substitute-model attack · UCF-101 and Kinetics-400Average ASR (%): 45.05 -> 44.06; 65.67 -> 66.04Mixed
Increase the number of interacted frames from n1=2 to n1=3 with n2=2 (ablation)VGG-16 substitute-model attack · UCF-101 and Kinetics-400Average ASR (%): 45.05 -> 42.90; 65.67 -> 64.46Hurt
Add LCD with λ=0.1 (ablation)VGG-16 substitute-model baseline · UCF-101 and Kinetics-400Average ASR (%): 36.63 -> 35.14; 56.42 -> 56.33Hurt
Add LCD with λ=0.01 (ablation)VGG-16 substitute-model baseline · UCF-101 and Kinetics-400Average ASR (%): 36.63 -> 38.61; 56.42 -> 58.75Improved
Add LCD with λ=0.001 (ablation)VGG-16 substitute-model baseline · UCF-101 and Kinetics-400Average ASR (%): 36.63 -> 37.29; 56.42 -> 56.33Mixed
Add GIE and LCD to I2V (ablation)Cross-modal attacks using DenseNet-121 · Kinetics-400Average ASR (%): I2V: 81.69; I2V+LCD: 82.00; GIE: 82.63; GIE+LCD: 84.00Improved
Use GIE+LCD with DenseNet-121+ResNet-101 instead of DenseNet-121GIE+LCD · Kinetics-400Average ASR (%): 84.00 -> 85.50Improved

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