You are currently viewing a new version of our website. To view the old version click .
Future Internet
  • This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
  • Article
  • Open Access

13 December 2025

Cross-Gen: An Efficient Generator Network for Adversarial Attacks on Cross-Modal Hashing Retrieval

,
,
,
,
,
,
and
1
School of Electronic Information, Central South University, Changsha 410083, China
2
China Telecom, Changsha 410083, China
3
Big Data Institute, Central South University, Changsha 410083, China
4
State Key Laboratory of Powder Metallurgy, Central South University, Changsha 410083, China
Future Internet2025, 17(12), 573;https://doi.org/10.3390/fi17120573 
(registering DOI)
This article belongs to the Special Issue Adversarial Attacks and Cyber Security

Abstract

Research on deep neural network (DNN)-based multi-dimensional data visualization has thoroughly explored cross-modal hash retrieval (CMHR) systems, yet their vulnerability to malicious adversarial examples remains evident. Recent work improves the robustness of CMHR networks by augmenting training datasets with adversarial examples. Prior approaches typically formulate the generation of cross-modal adversarial examples as an optimization problem solved through iterative methods. Although effective, such techniques often suffer from slow generation speed, limiting research efficiency. To address this, we propose a generative-based method that enables rapid synthesis of adversarial examples via a carefully designed adversarial generator network. Specifically, we introduce Cross-Gen, a parallel cross-modal framework that constructs semantic triplet data by interacting with the target model through query-based feedback. The generator is optimized using a tailored objective comprising adversarial loss, reconstruction loss, and quantization loss. The experimental results show that Cross-Gen generates adversarial examples significantly faster than iterative methods while achieving competitive attack performance.

Article Metrics

Citations

Article Access Statistics

Article metric data becomes available approximately 24 hours after publication online.