A Two-Stage Generative Adversarial Networks With Semantic Content Constraints for Adversarial Example Generation

Tian, Yu; Zhang, Ru; Sun, Youqiang; Wang, Chan

doi:10.1109/access.2020.3037329

Cited by 9 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An example of supervised domain adaptation is the work of Goodman et al [37] whose approach was based on the transfer of the gradient history of the pre-training phase to the fine-tuning phase, while also trying to improve generalization by optimal parameterization during the pre-training phase. Liu et al [38] exploited generative adversarial training with cycle consistency constraints, enabling a cross-domain style transformation. On the other hand, Ganin and Lempitsky [39] showcased an unsupervised domain adaptation scheme, assuming lack of access to any labeled data from the target domain.…”

Section: Domain Adaptationmentioning

confidence: 99%

See 1 more Smart Citation

A Multi-Modal Egocentric Activity Recognition Approach towards Video Domain Generalization

Papadakis,

Spyrou

2024

Sensors

View full text Add to dashboard Cite

Egocentric activity recognition is a prominent computer vision task that is based on the use of wearable cameras. Since egocentric videos are captured through the perspective of the person wearing the camera, her/his body motions severely complicate the video content, imposing several challenges. In this work we propose a novel approach for domain-generalized egocentric human activity recognition. Typical approaches use a large amount of training data, aiming to cover all possible variants of each action. Moreover, several recent approaches have attempted to handle discrepancies between domains with a variety of costly and mostly unsupervised domain adaptation methods. In our approach we show that through simple manipulation of available source domain data and with minor involvement from the target domain, we are able to produce robust models, able to adequately predict human activity in egocentric video sequences. To this end, we introduce a novel three-stream deep neural network architecture combining elements of vision transformers and residual neural networks which are trained using multi-modal data. We evaluate the proposed approach using a challenging, egocentric video dataset and demonstrate its superiority over recent, state-of-the-art research works.

show abstract

Section: Domain Adaptationmentioning

confidence: 99%

“…Liu et al. [ 38 ] exploited generative adversarial training with cycle consistency constraints, enabling a cross-domain style transformation. On the other hand, Ganin and Lempitsky [ 39 ] showcased an unsupervised domain adaptation scheme, assuming lack of access to any labeled data from the target domain.…”

Section: Related Workmentioning

confidence: 99%

A Multi-Modal Egocentric Activity Recognition Approach towards Video Domain Generalization

Papadakis,

Spyrou

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Sharif et al [44] proposed a general framework, adversarial generative nets (AGNs), to generate adversarial examples satisfying desired objectives by training a generator in AGNs. Liu et al [45] proposed a two-stage generative adversarial networks with semantic content constraints to generate adversarial examples satisfying predefined semantic constraints. Tang et al [46] proposed a distance constrained adversarial imitation network (AIN).…”

Section: Related Workmentioning

confidence: 99%

DCVAE-adv: A Universal Adversarial Example Generation Method for White and Black Box Attacks

Xu,

Zhai

2024

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

Deep neural network (DNN) has strong representation learning ability, but it is vulnerable and easy to be fooled by adversarial examples. In order to handle the vulnerability of DNN, many methods have been proposed.The general idea of existing methods is to reduce the chance of DNN models being fooled by observing some designed adversarial examples, which are generated by adding perturbations to the original images. In this paper, we propose a novel adversarial example generation method, called DCVAE-adv. Different from the existing methods, DCVAE-adv constructs adversarial examples by mixing both explicit and implicit perturbations without using original images. Furthermore, the proposed method can be applied to both white box and black box attacks. In addition, in the inference stage, the adversarial examples can be generated without loading the original images into memory, which greatly reduces the memory overhead. We compared DCVAE-adv with three most advanced adversarial attack algorithms: FGSM, AdvGAN, and AdvGAN++. The experimental results demonstrate that DCVAE-adv is superior to these state-of-the-art methods in terms of attack success rate and transfer ability for targeted attack. Our code is available at https://github.com/xzforeverlove/DCVAE-adv.

show abstract

DeepMC: DNN test sample optimization method jointly guided by misclassification and coverage

Sun

Wen

2022

Appl Intell

View full text Add to dashboard Cite

A Two-Stage Generative Adversarial Networks With Semantic Content Constraints for Adversarial Example Generation

Cited by 9 publications

References 18 publications

A Multi-Modal Egocentric Activity Recognition Approach towards Video Domain Generalization

A Multi-Modal Egocentric Activity Recognition Approach towards Video Domain Generalization

DCVAE-adv: A Universal Adversarial Example Generation Method for White and Black Box Attacks

DeepMC: DNN test sample optimization method jointly guided by misclassification and coverage

Contact Info

Product

Resources

About