Generating universal adversarial perturbation with ResNet

Xu, Jian; Liu, Heng; Wu, Dexin; Fang, Zhou; Gao, Chongzhi; Jiang, Linzhi

doi:10.1016/j.ins.2020.05.099

Cited by 11 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hao et al proposed a method based on convolutional sparse self-coding neural network, which has been proved to have good classification performance [8]. Nowadays, with the continuous development of deep learning technology, there are many networks with better performance and larger scale, such as Google Net [9], ResNet [10], and DenseNet [11]. Tiktok, Kwai, and today's headlines are the short video resources represented by [12], which makes it impossible to detect and extract facial expression's facial features and facial expression accurately.…”

Section: Related Workmentioning

confidence: 99%

Short Video Copyright Storage Algorithm Based on Blockchain and Expression Recognition

Yang

2022

International Journal of Digital Multimedia Broadcasting

View full text Add to dashboard Cite

Blockchain technology is widely used in the field of digital right protection technology. The traditional digital right protection scheme is not only inefficient and highly centralized but also has the risk of being modified. Due to its own characteristics, blockchain cannot completely store all the original files of digital resources. In this paper, a convolutional neural network algorithm based on visual priority rule is proposed (CNNVP). This algorithm can recognize facial expressions in the original files of digital resources (for short video of face class). The algorithm extracts facial expression features accurately and makes these features form log files that can represent the original files of digital resources. Then, the paper proposes a short video copyright storage algorithm based on blockchain and facial expression recognition and stores the log file into the blockchain. The above methods not only improve the efficiency of short video copyright storage, reduce the degree of storage centralization, and eliminate the risk that copyright is easy to be modified. Moreover, the computing operation of deep learning technology on short video not only ensures the privacy of storage certificate information but also ensures the possibility of blockchain storage of video information. Experiments show that the algorithm proposed in this paper is more efficient than the traditional copyright storage method. Moreover, the algorithm proposed in this paper can provide technical support to the media resource management department.

show abstract

Section: Related Workmentioning

confidence: 99%

Short Video Copyright Storage Algorithm Based on Blockchain and Expression Recognition

Yang

2022

International Journal of Digital Multimedia Broadcasting

View full text Add to dashboard Cite

show abstract

“…Xu [13] proposed to use the residual network generator to generate universal perturbations, and can effectively add perturbations to any original sample after training. Different from the traditional method, this method adds a loss network, which can make the adversarial examples with perturbations visually similar to the original sample to a certain extent.…”

Section: Adversarial Attacks Based On Generative Adversarial Network ...mentioning

confidence: 99%

Research on adversarial attacks and defense

Xie

Zhang

Xiang

2022

International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2022)

View full text Add to dashboard Cite

Deep learning is widely used in our daily life to solve some complex and tedious problems. In practical applications, if it was exploited by attackers would affect the reliability and security of the deep learning model. This article mainly introduces some attacks methods of generating adversarial examples from Generative Adversarial Networks(GAN) in recent years and related algorithms that use adversarial training to improve the robustness of deep learning models. At the end of the article, drawing on the reviewed literature, we present a broader outlook of adversarial attacks research direction.

show abstract

“…In this paper, the adversarial attack is interpreted as a scheme to increase perturbations in the image data. The perturbation is generated and added in multi-steps as follows [6,7]:…”

Section: Adversarial Attacksmentioning

confidence: 99%

Deep Learning Network Model Studies for Adversarial Attack Resistance

Chen

Choi

2021

Intelligent and Fuzzy Techniques for Emerging Conditions and Digital Transformation

View full text Add to dashboard Cite

In the last decades, deep learning neural networks have taken several steps toward higher pattern recognition accuracies. Face recognition is one of the popular topics that have drawn much attention and it is now frequently used in everyday lives. However, the recognition performance suffers easily by irregularities and disturbances. The focus of this work is to explore the security performance of deep learning neural networks by using an adversarial attack approach. The ResNets is the framework of the proposed system and its recognition behaviors under the adversarial attacks are investigated. The experiments are performed by using MNIST and CIFAR-10 datasets and the detection and recognition errors are evaluated. The results show that the proposed systems can be an alternative that can resist perturbations better than the conventional models.

show abstract

Generating universal adversarial perturbation with ResNet

Cited by 11 publications

References 4 publications

Short Video Copyright Storage Algorithm Based on Blockchain and Expression Recognition

Short Video Copyright Storage Algorithm Based on Blockchain and Expression Recognition

Research on adversarial attacks and defense

Deep Learning Network Model Studies for Adversarial Attack Resistance

Contact Info

Product

Resources

About