AI Paper Atlas

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

Prototype-Supervised Adversarial Network for Targeted Attack of Deep Hashing

Xunguang Wang, Zheng Zhang, Baoyuan Wu, Fumin Shen, Guangming Lu

CVPR 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Defenses against universal perturbations · 54 citations (OpenAlex)

Check 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 ProS-GAN instead of DHTADPSH hashing retrieval · FLICKR-25K, 32 bitst-MAP: 88.35 -> 91.10Improved
Use ProS-GAN instead of DHTADPSH hashing retrieval · NUS-WIDE, 32 bitst-MAP: 75.65 -> 78.25Improved
Use ProS-GAN instead of DHTADPSH hashing retrieval · MS-COCO, 32 bitst-MAP: 63.22 -> 71.65Improved
Add prototype-code supervision using the Hamming distance loss (ablation)ProS-GAN · NUS-WIDEt-MAPImproved
Add the discriminator classification module (ablation)ProS-GAN · NUS-WIDE, varying hash bitst-MAPImproved
Increase the reconstruction-loss weight α (ablation)ProS-GAN · NUS-WIDE, 32 bitsperceptibilityImproved
Increase the reconstruction-loss weight α (ablation)ProS-GAN · NUS-WIDE, 32 bitst-MAPHurt
Use learned prototype codes instead of anchor codestargeted hashing attack · FLICKR-25K, 32 bitst-MAP: 88.68 -> 92.91Improved
Use learned prototype codes instead of anchor codestargeted hashing attack · NUS-WIDE, 32 bitst-MAP: 78.40 -> 81.34Improved
Use learned prototype codes instead of anchor codestargeted hashing attack · MS-COCO, 32 bitst-MAP: 64.41 -> 71.93Improved

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