AI Paper Atlas

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

Targeted Attack for Deep Hashing based Retrieval

Jiawang Bai, Bin Chen, Yiming Li, Dongxian Wu, Weiwei Guo, Shu-Tao Xia, En-Hui Yang

ECCV 2020 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks

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 point-to-set anchor code with n_t=9 instead of point-to-point (n_t=1) targetDHTA · ImageNet (16 bits)t-MAP (%): 44.35 -> 63.68Improved
use point-to-set anchor code instead of point-to-point targetDHTA · JHMDB (64 bits)t-MAP (%): 44.38 -> 66.06Improved
use point-to-set anchor code instead of point-to-point targetDHTA · NUS-WIDE (HashNet target, 16 bits)t-MAP (%): 78.10 -> 86.95Improved
increase object set size n_t beyond 1 (ablation)DHTA · ImageNet and JHMDBt-MAP (%)Improved
increase n_t from 5 to 11 in open-set attack (ablation)DHTA · ImageNet open-set (16 bits)t-MAP (%): 33.67 -> 38.00Improved
increase attack iterations from 100 to 2000 (ablation)DHTA · ImageNet (32 bits)t-MAP (%): 66.29 -> 77.76Improved
increase attack iterations from 10 to 500 (ablation)DHTA · JHMDB (16 bits)t-MAP (%): 28.51 -> 56.47Improved
increase epsilon from 0.01 to 0.05 (ablation)DHTA · ImageNet (32 bits)t-MAP (%): 25.39 -> 79.17Improved
increase epsilon from 0.01 to 0.05 (ablation)DHTA · JHMDB (32 bits)t-MAP (%): 51.08 -> 62.76Improved
attack in Hamming space instead of feature spaceFeature-based attack · ImageNet (16 bits)t-MAP (%): 23.80 -> 63.68Improved
attack in Hamming space instead of feature spaceFeature-based attack · JHMDB (64 bits)t-MAP (%): 57.54 -> 66.06Mixed
use DHTA as a non-targeted attack versus HAGHAG · ImageNet (16 bits) MAPMAP (%): 1.88 -> 0.54Improved

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