AI Paper Atlas

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

Black-Box Adversarial Attack on Time Series Classification

Daizong Ding, Mi Zhang, Fuli Feng, Yuanmin Huang, Erling Jiang, Min Yang

AAAI 2023 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 14 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
apply BlackTreeS instead of PGDLSTM attack on UWave · UWaveASR: 21.6% -> 27.3%Improved
apply BlackTreeS instead of AutoZOOMLSTM attack on UWave · UWaveDSR: 90.9% -> 6.8%Improved
add tree position search rather than select positions randomly (ablation)BlackTreeS · UWaveASR: 27.5% -> 57.5%Improved
add tree position search rather than select positions randomly (ablation)BlackTreeS · UWaveDSR: 49.8% -> 14.3%Improved
add tree position search rather than select positions randomly (ablation)BlackTreeS · ClimateASR: 50.3% -> 70.3%Improved
add tree position search rather than select positions randomly (ablation)BlackTreeS · EyeDSR: 53.5% -> 22.0%Improved
use independent instead of joint gradient approximation (ablation)BlackTreeS position selection on UWave BiRNN · UWaveACC for selecting top 50 positions: 76.4% -> 96.1%Improved
use independent instead of joint gradient approximation (ablation)BlackTreeS gradient estimation on UWave BiRNN · UWaveRMSE: 0.138 -> 0.060Improved

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