A Novel Multi-Sample Generation Method for Adversarial Attacks

Duan, Mingxing; Li, Kenli; Deng, Jiayan; Xiao, Bin

doi:10.1145/3506852

Cited by 21 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It summarizes the attack behaviors for enterprise into 222 sub‐technologies in 14 categories such as reconnaissance, resource development, initial access, execution according to stages and so forth and is continuously updated. Duan et al 9 proposed a MsGM method for black‐box attacks. Paper 10 pointed out that adversarial training using adversarial examples generated by MBbA can improve the robustness of the attacked models.…”

Section: Related Workmentioning

confidence: 99%

An active defense model based on situational awareness and firewalls

Xiao

et al. 2023

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

With the rapid development of the internet, cyberspace security issues have become increasingly prominent. The importance of constructing a cyberspace security system is self-evident, but compared with attackers, defenders in cyberspace are in a castle-like passive defense state in most cases. Therefore, building a reliable, accurate, timely, and active defense system is challenging. The key is to accurately focus on defense priorities, the anticipation of attackers who will likely succeed, and blocking attacks in a timely manner. In this article, we propose an active defense model based on the interaction of situational awareness and firewalls. First, by biasing the integrity, confidentiality, and availability of assets to get the score of assets, and using the Common Vulnerability Scoring System to assess the threat level of assets, we combine the two to determine the maximum system damage that the asset will suffer if it is lost, and then focus on defense. Meanwhile, log analysis of the network situational awareness platform can predict successful attackers, and then the linked firewall strategy can block these attacks in time before the attackers obtain attack gains. After that, we force the attackers to give up their attacks on the target by increasing the attack cost.We compared our model with iptables auto-blocking and nginx auto-blocking, and our model excelled them across the board in terms of comprehensiveness and false positive rate. The experimental results verify thar our active defense model proposed in this article can better reduce the defense cost and increase the attack cost, thus achieving the relatively defense goal. K E Y W O R D Sactive defense, cyber attack and defense, defense cost, game theory INTRODUCTIONWith the development of information technology, cyberspace has become the fifth space after "land, sea, air, and sky", and the security of cyberspace is directly related to the sovereign security of the country. Cyber attack and defense have become hot spots in current cybersecurity research. The objectives of cyber attackers include collecting information about a target, paralyzing the target service, entering the target and stealing data, while the objectives of cyber defenders are to keep the service running normally and stop attackers. Scanning of the target system is something that a cyber attacker must do before launching cyber attacks, which helps the attacker gain access to exploitable vulnerabilities in the target system to compromise the network. The purpose of such a scan is to understand the configurations of target systems, including but not limited to the target system's operating system, IP address, running services, software versions, existing common vulnerabilities & exposures(CVEs), weak passwords, and so on. How to prevent attackers from obtaining the scan results or prevent the attacker from using the scan results for other benefits is the goal

show abstract

Section: Related Workmentioning

confidence: 99%

An active defense model based on situational awareness and firewalls

Xiao

et al. 2023

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, they emphasize that the user's choice is important. As proposed by the authors [19], MsGM is a multi-sample generation model for black-box model attacks that uses a large number of samples. Multi-sample generation, replacement model training, and adversarial sample generation and attack are primarily made up of three parts.…”

Section: Real-time Approachesmentioning

confidence: 99%

SETTI: A S elf-supervised Adv E rsarial Malware De T ection Archi T ecture in an I oT Environment

Golmaryami

Taheri

Pooranian

et al. 2022

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

In recent years, malware detection has become an active research topic in the area of Internet of Things (IoT) security. The principle is to exploit knowledge from large quantities of continuously generated malware. Existing algorithms practise available malware features for IoT devices and lack real-time prediction behaviours. More research is thus required on malware detection to cope with real-time misclassification of the input IoT data. Motivated by this, in this paper we propose an adversarial self-supervised architecture for detecting malware in IoT networks, SETTI, considering samples of IoT network traffic that may not be labeled. In the SETTI architecture, we design three self-supervised attack techniques, namely Self-MDS , GSelf-MDS and ASelf-MDS . The Self-MDS method considers the IoT input data and the adversarial sample generation in real-time. The GSelf-MDS builds a generative adversarial network model to generate adversarial samples in the self-supervised structure. Finally, ASelf-MDS utilizes three well-known perturbation sample techniques to develop adversarial malware and inject it over the self-supervised architecture. Also, we apply a defence method to mitigate these attacks, namely adversarial self-supervised training to protect the malware detection architecture against injecting the malicious samples. To validate the attack and defence algorithms, we conduct experiments on two recent IoT datasets: IoT23 and NBIoT. Comparison of the results shows that in the IoT23 dataset, the Self-MDS method has the most damaging consequences from the attacker’s point of view by reducing the accuracy rate from 98% to 74%. In the NBIoT dataset, the ASelf-MDS method is the most devastating algorithm that can plunge the accuracy rate from 98% to 77%.

show abstract

“…As proposed by the authors [19], MsGM is a multi-sample generation model for black-box model attacks that uses a large number of samples. Multi-sample generation, replacement model training, and adversarial sample generation and attack are primarily made up of three parts.…”

Section: Real-time Approachesmentioning

confidence: 99%

SETTI: A Self-supervised Adversarial Malware Detection Architecture in an IoT Environment

Golmaryami¹,

Taheri²,

Pooranian³

et al. 2022

Preprint

View full text Add to dashboard Cite

In recent years, malware detection has become an active research topic in the area of Internet of Things (IoT) security. The principle is to exploit knowledge from large quantities of continuously generated malware. Existing algorithms practise available malware features for IoT devices and lack real-time prediction behaviours. More research is thus required on malware detection to cope with real-time misclassification of the input IoT data. Motivated by this, in this paper we propose an adversarial self-supervised architecture for detecting malware in IoT networks, SETTI, considering samples of IoT network traffic that may not be labeled. In the SETTI architecture, we design three self-supervised attack techniques, namely Self-MDS, GSelf-MDS and ASelf-MDS. The Self-MDS method considers the IoT input data and the adversarial sample generation in real-time. The GSelf-MDS builds a generative adversarial network model to generate adversarial samples in the self-supervised structure. Finally, ASelf-MDS utilizes three well-known perturbation sample techniques to develop adversarial malware and inject it over the self-supervised architecture. Also, we apply a defence method to mitigate these attacks, namely adversarial self-supervised training to protect the malware detection architecture against injecting the malicious samples. To validate the attack and defence algorithms, we conduct experiments on two recent IoT datasets: IoT23 and NBIoT. Comparison of the results shows that in the IoT23 dataset, the Self-MDS method has the most damaging consequences from the attacker's point of view by reducing the accuracy rate from 98% to 74%. In the NBIoT dataset, the ASelf-MDS method is the most devastating algorithm that can plunge the accuracy rate from 98% to 77%.

show abstract

A Novel Multi-Sample Generation Method for Adversarial Attacks

Cited by 21 publications

References 39 publications

An active defense model based on situational awareness and firewalls

An active defense model based on situational awareness and firewalls

SETTI: A S elf-supervised Adv E rsarial Malware De T ection Archi T ecture in an I oT Environment

SETTI: A Self-supervised Adversarial Malware Detection Architecture in an IoT Environment

Contact Info

Product

Resources

About