SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.08868 · 2021

Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

A backdoored deep hashing model is expected to behave normally on original query images and return the images with the target label when a specific trigger pattern presents. To this end, we propose the confusing perturbations-induced backdoor attack (CIBA). It injects a small number of poisoned images with the correct label into the training data, which makes the attack hard to be detected. To craft the poisoned images, we first propose the confusing perturbations to disturb the hashing code learning. As such, the hashing model can learn more about the trigger. The confusing perturbations are imperceptible and generated by optimizing the intra-class dispersion and inter-class shift in the Hamming space. We then employ the targeted adversarial patch as the backdoor trigger to improve the attack performance. We have conducted extensive experiments to verify the effectiveness of our proposed CIBA. Our code is available at https://github.com/KuofengGao/CIBA.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2109.08868")
get_code_for_paper("2109.08868")
have("2109.08868")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2109.08868.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2109.08868.svg)](https://syntology.ai/paper/2109.08868)

Connect an agent — have() is free.