Adversarial Attacks on License Plate Recognition Systems

Gu, Zhaoquan; Su, Yu; Liu, Chenwei; Lyu, Yinyu; Jian, Yunxiang; Li, Hao; Cao, Zhen; Wang, Le

doi:10.32604/cmc.2020.011834

Cited by 15 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, the use of DNNs have been found in lane line detection and traffic sign recognition in self-driving cars [3][4][5], Unmanned Aerial Vehicle (UAV)-based monitoring system [6], and even to the usage in the emerging technologies and framework such as big data [7] and blockchain [8] in the industrial network infrastructure. Despite their promising progress, recent research has shown examples of attacks on various intelligent systems [9,10]. In particular, it is known that DNNs included in those systems are vulnerable to adversarial attacks, which lead deep learning models to make incorrect predictions with high confidence.…”

Section: Introductionmentioning

confidence: 99%

Extended Spatially Localized Perturbation GAN (eSLP-GAN) for Robust Adversarial Camouflage Patches

Kim

Kang

Suryanto

et al. 2021

Sensors

View full text Add to dashboard Cite

Deep neural networks (DNNs), especially those used in computer vision, are highly vulnerable to adversarial attacks, such as adversarial perturbations and adversarial patches. Adversarial patches, often considered more appropriate for a real-world attack, are attached to the target object or its surroundings to deceive the target system. However, most previous research employed adversarial patches that are conspicuous to human vision, making them easy to identify and counter. Previously, the spatially localized perturbation GAN (SLP-GAN) was proposed, in which the perturbation was only added to the most representative area of the input images, creating a spatially localized adversarial camouflage patch that excels in terms of visual fidelity and is, therefore, difficult to detect by human vision. In this study, the use of the method called eSLP-GAN was extended to deceive classifiers and object detection systems. Specifically, the loss function was modified for greater compatibility with an object-detection model attack and to increase robustness in the real world. Furthermore, the applicability of the proposed method was tested on the CARLA simulator for a more authentic real-world attack scenario.

show abstract

Section: Introductionmentioning

confidence: 99%

Extended Spatially Localized Perturbation GAN (eSLP-GAN) for Robust Adversarial Camouflage Patches

Kim

Kang

Suryanto

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…With the fast development of artificial intelligent technologies, deep learning models have been widely adopted in more and more areas [1][2][3]. In particular, they have been adopted not only in target detection, image classification, and other applications in the field of CV (Computer Vision) [4,5] but also in more and more NLP (Nature Language Processing) applications, such as sentiment classification, spam classification, and machine translation [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Exploring Security Vulnerabilities of Deep Learning Models by Adversarial Attacks

Han

et al. 2021

Wireless Communications and Mobile Computing

Self Cite

View full text Add to dashboard Cite

Nowadays, deep learning models play an important role in a variety of scenarios, such as image classification, natural language processing, and speech recognition. However, deep learning models are shown to be vulnerable; a small change to the original data may affect the output of the model, which may incur severe consequences such as misrecognition and privacy leakage. The intentionally modified data is referred to as adversarial examples. In this paper, we explore the security vulnerabilities of deep learning models designed for textual analysis. Specifically, we propose a visual similar word replacement (VSWR) algorithm to generate adversarial examples against textual analysis models. By using adversarial examples as the input of deep learning models, we verified that deep learning models are vulnerable to such adversarial attacks. We have conducted experiments on several sentiment analysis deep learning models to evaluate the performance. The results also confirmed that the generated adversarial examples could successfully attack deep learning models. As the number of modified words increases, the model prediction accuracy becomes lower. This kind of adversarial attack implies security vulnerabilities of deep learning models.

show abstract

“…This is especially true in image recognition because a minor tweak on the image (without affecting normal classification by human) may lead the neural networks to errors [ 14 ] . Adversarial examples prevail not only in image recognition, but also in audio and text recognition [ 15 , 16 ] .…”

Section: Introductionmentioning

confidence: 99%

Marginal Attacks of Generating Adversarial Examples for Spam Filtering

Xie

et al. 2021

Chinese J of Electronics

View full text Add to dashboard Cite

Digit information has been used in many areas and has been widely spread in the Internet era because of its convenience. However, many ill-disposed attackers, such as spammers take advantage of such convenience to send unsolicited information, such as advertisements, frauds, and pornographic messages to mislead users and this might cause severe consequences. Although many spam filters have been proposed in detecting spams, they are vulnerable and could be misled by some carefully crafted adversarial examples. In this paper, we propose the marginal attack methods of generating such adversarial examples to fool a naive Bayesian spam filter.Specifically, we propose three methods to select sensitive words from a sentence and add them at the end of the sentence. Through extensive experiments, we show that the generated adversarial examples could largely reduce the filter's detecting accuracy, e.g. by adding only one word, the accuracy could be reduced from 93.6% to 55.8%. Furthermore, we evaluate the transferability of the generated adversarial examples against other traditional filters such as logic regression, decision tree and linear support vector machine based filters.The evaluation results show that these filters'accuracy is also reduced dramatically; especially, the decision tree based filter's accuracy drops from 100% to 1.51% by inserting only one word.

show abstract

Adversarial Attacks on License Plate Recognition Systems

Cited by 15 publications

References 0 publications

Extended Spatially Localized Perturbation GAN (eSLP-GAN) for Robust Adversarial Camouflage Patches

Extended Spatially Localized Perturbation GAN (eSLP-GAN) for Robust Adversarial Camouflage Patches

Exploring Security Vulnerabilities of Deep Learning Models by Adversarial Attacks

Marginal Attacks of Generating Adversarial Examples for Spam Filtering

Contact Info

Product

Resources

About