AI Paper Atlas

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

Efficient Adversarial Attacks for Visual Object Tracking

Siyuan Liang, Xingxing Wei, Siyuan Yao, Xiaochun Cao

ECCV 2020 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 77 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
use FAN drift loss generator instead of modified FGSMuntargeted tracker attack · OTB2013success score drop rate: 3% -> 74%Improved
use FAN instead of modified PGDuntargeted tracker attack · OTB2013success score drop rate: 3% -> 74%Improved
use FAN generator instead of iterative PGD for speeduntargeted tracker attack · OTB2013time per sample (s): 3.53 -> 0.01Improved
transfer FAN adversarial examples from SiamFC to SiamRPN++ (black-box)FAN · OTB2013success score drop rate: 74% -> 33%Hurt
transfer FAN adversarial examples from SiamFC to SiamRPN (black-box)FAN · OTB2013success score drop rate: 74% -> 55%Hurt
increase embedding loss weight alpha2 within 0.05-0.1 (ablation)FAN targeted attack · OTBprecision score: precision score improves ten percentageImproved
apply FAN targeted attack on VOT2014SiamFC · VOT2014frames per restart: 108.8 -> 14Improved
use targeted instead of untargeted attack objectiveFAN · OTB2013drop rate: 76% -> 40.6%Hurt

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