The security of machine learning in an adversarial setting: A survey

Wang, Xianmin; Li, Jing; Kuang, Xiaohui; Tan, Yuan

doi:10.1016/j.jpdc.2019.03.003

Cited by 175 publications

(134 citation statements)

References 36 publications

Supporting

Mentioning

134

Contrasting

Order By: Relevance

“…Model-based predictions could help to identify opportunities to improve market regulations. Another area of opportunity is to help platforms and fraud detection firms design better approaches to detect and reverse ad fraud. In general, the topic of how to attack machine learning algorithms and how to resist attack is a topic of active research (e.g., Wang et al 2019). Consideration of adversarial methods may help firms anticipate and defend against future developments in fraud technology.…”

Section: Digital Advertising Fraudmentioning

confidence: 99%

Inefficiencies in Digital Advertising Markets

Gordon¹,

Jerath

Katona

et al. 2020

Journal of Marketing

112

View full text Add to dashboard Cite

Digital advertising markets are growing and attracting increased scrutiny. This article explores four market inefficiencies that remain poorly understood: ad effect measurement, frictions between and within advertising channel members, ad blocking, and ad fraud. Although these topics are not unique to digital advertising, each manifests in unique ways in markets for digital ads. The authors identify relevant findings in the academic literature, recent developments in practice, and promising topics for future research.

show abstract

Section: Digital Advertising Fraudmentioning

confidence: 99%

Inefficiencies in Digital Advertising Markets

Gordon¹,

Jerath

Katona

et al. 2020

Journal of Marketing

112

View full text Add to dashboard Cite

show abstract

“…Zhang et al [7] proposed an approach for crowed assessing the security and trustworthiness of open social networks based on signaling theory. e authors [5] presented a detailed overview of the security properties investigation of machine learning algorithms. ey have analysed the security model of ML to build up a blueprint for multidisciplinary area of research and, after that, the attack methods and discussed the strategies of defense against them.…”

Section: Related Workmentioning

confidence: 99%

“…e technology is ever playing an important role in human life and made things easy. With the developments of technology, security remains one of the major concerns for communication and interaction [1][2][3][4][5][6][7][8][9][10]. Since the last few decades, the attacks on information security become raised and intruders are trying to capture ordination important information for their own benefits.…”

Section: Introductionmentioning

confidence: 99%

Convolution Neural Network-Based Higher Accurate Intrusion Identification System for the Network Security and Communication

Gu¹,

Nazir

Hong³

et al. 2020

Security and Communication Networks

View full text Add to dashboard Cite

With the development of communication systems, information securities remain one of the main concerns for the last few years. The smart devices are connected to communicate, process, compute, and monitor diverse real-time scenarios. Intruders are trying to attack the network and capture the organization’s important information for its own benefits. Intrusion detection is a way of identifying security violations and examining unwanted occurrences in a computer network. Building an accurate and effective identification system for intrusion detection or malicious activities can secure the existing system for smooth and secure end-to-end communication. In the proposed research work, a deep learning-based approach is followed for the accurate intrusion detection purposes to ensure the high security of the network. A convolution neural network based approach is followed for the feature classification and malicious data identification purposes. In the end, comparative results are generated after evaluating the performance of the proposed algorithm to other rival algorithms in the proposed field. These comparative algorithms were FGSM, JSMA, C&W, and ENM. After evaluating the performance of these algorithms and the proposed algorithm based on different threshold values ranging, Lp norms, and different parametric values for c, it was concluded that the proposed algorithm outperforms with small Lp values and high Kitsune scores. These results reflect that the proposed research is promising toward the identification of attack on data packets, and it also reflects the applicability of the proposed algorithms in the network security field.

show abstract

“…The network communication rules between each server and the host are configured through a firewall [38]. The network is divided into three areas.…”

Section: A Experimental Environmentmentioning

confidence: 99%

I-HMM-Based Multidimensional Network Security Risk Assessment

Zhang

Guo

Kuang³

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Cyber-physical systems (CPS) are vulnerable to network attacks because communication relies on the network that links the various components in the CPS. The importance of network security is selfevident. In this study, we conduct a network security risk assessment from the perspectives of the host and the network, and we propose a new framework for a multidimensional network security risk assessment that includes two stages, i.e., risk identification and risk calculation. For the risk identification stage, we propose a multidimensional hierarchical index system for assessing cybersecurity risk; the system's security status is determined in three dimensions, i.e., basic operation, vulnerabilities, and threats, and these dimensions guide the data collection. In the risk calculation stage, we use a hidden Markov model (HMM) to assess the network security risk. We provide a new definition of the quality of alert and optimize the observation sequence of the HMM. The model uses a learning algorithm instead of setting the parameters manually. We introduce the concept of network node association to increase the reliability and accuracy of the risk assessment. The simulation results show that the proposed index system provides quantitative data that reflect the security status of the network. The proposed network security risk assessment method based on the improved HMM (I-HMM) reflects the security risk status in a timely and intuitive manner and detects the degree of risk that different hosts pose to the network. INDEX TERMS Hidden Markov model, network node correlation, network security risk, risk assessment. I. INTRODUCTION Cyber-physical systems (CPS) are complex systems that use sensors, computing and network technology for computation, communication and control to link the physical world and the network. Since the communication of the CPS relies on a network, CPS are plagued by security issues [1], [2]. Malicious activities that specifically target networks [3], [4] and security incidents are occurring with increasing frequency [5]. The types of network security incidents [6] include information system vulnerabilities, phishing, and malicious programs [7]. There are two reasons for the occurrence of network security incidents [8]. First, weak links exist in the network system [9] and second, the emergence of various automated attack tools has caused a sharp increase in intrusions into network systems [10], [11]. The associate editor coordinating the review of this manuscript and approving it for publication was Zhen Ling.

show abstract

The security of machine learning in an adversarial setting: A survey

Cited by 175 publications

References 36 publications

Inefficiencies in Digital Advertising Markets

Inefficiencies in Digital Advertising Markets

Convolution Neural Network-Based Higher Accurate Intrusion Identification System for the Network Security and Communication

I-HMM-Based Multidimensional Network Security Risk Assessment

Contact Info

Product

Resources

About