A Survey on Security Threats and Defensive Techniques of Machine Learning: A Data Driven View

Liu, Qiang; Pan, Li; Zhao, Wentao; Cai, Wei; Yu, Shui; Leung, Victor C. M.

doi:10.1109/access.2018.2805680

Cited by 338 publications

(199 citation statements)

References 62 publications

Supporting

Mentioning

195

Contrasting

Unclassified

Order By: Relevance

“…These algorithms are susceptible to many threats that either decrease the accuracy and performance of the classifiers or expose sensitive data used in the training process of the classifiers. Examples of the potential threats that can be utilised by attackers include poisoning, evasion, impersonation and inversion attacks s [272]. Poisoning is a threat in which the attacker injects malicious samples with incorrect labels into the training dataset to modify training data distribution, decrease the discrimination power of the classifier in distinguishing between the normal and abnormal behaviour of the system, and ultimately decrease classifier accuracy and performance.…”

Section: ) Security Of ML and Dl Methodsmentioning

confidence: 99%

A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security

Al-Garadi

Mohamed

Al-Ali

et al. 2020

IEEE Commun. Surv. Tutorials

838

333

View full text Add to dashboard Cite

The Internet of Things (IoT) integrates billions of smart devices that can communicate with one another with minimal human intervention. It is one of the fastest developing fields in the history of computing, with an estimated 50 billion devices by the end of 2020. On the one hand, IoT technologies play a crucial role in enhancing several real-life smart applications that can improve life quality. On the other hand, the crosscutting nature of IoT systems and the multidisciplinary components involved in the deployment of such systems have introduced new security challenges. Implementing security measures, such as encryption, authentication, access control, network security and application security, for IoT devices and their inherent vulnerabilities is ineffective. Therefore, existing security methods should be enhanced to secure the IoT ecosystem effectively. Machine learning and deep learning (ML/DL) have advanced considerably over the last few years, and machine intelligence has transitioned from laboratory curiosity to practical machinery in several important applications. The ability to monitor IoT devices intelligently provides a significant solution to new or zero-day attacks. ML/DL are powerful methods of data exploration for learning about 'normal' and 'abnormal' behaviour according to how IoT components and devices perform within the IoT environment. Consequently, ML/DL methods are important in transforming the security of IoT systems from merely facilitating secure communication between devices to security-based intelligence systems. The goal of this work is to provide a comprehensive survey of ML methods and recent advances in DL methods that can be used to develop enhanced security methods for IoT systems.IoT security threats that are related to inherent or newly introduced threats are presented, and various potential IoT system attack surfaces and the possible threats related to each surface are discussed. We then thoroughly review ML/DL methods for IoT security and present the opportunities, advantages and shortcomings of each method. We discuss the opportunities and challenges involved in applying ML/DL to IoT security. These opportunities and challenges can serve as potential future research directions.

show abstract

Section: ) Security Of ML and Dl Methodsmentioning

confidence: 99%

A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security

Al-Garadi

Mohamed

Al-Ali

et al. 2020

IEEE Commun. Surv. Tutorials

838

333

View full text Add to dashboard Cite

show abstract

“…e researchers [81,83,84] proposed different techniques to detect adversarial examples in the input and to create different benign and adversarial examples. As we mentioned earlier, the target of the attacker is to add more noise to formulate [47] Changes the discriminant results Resource consuming [50][51][52] Misclassifies positive sample Integrity attack [53] False negative passes through the system Easily detected [54][55][56] Availability attack [57] False positive results in blocking records Time and resource consuming [58][59][60] Privacy violation attack [61] Easily exploit the training dataset Its performance is not reliable as it based on iterations [62][63][64] Targeted attack [65] Misclassified to any arbitrary class It does not provide assurance about the generated samples [66][67][68] Indiscriminate attack [69] Good trade-off Perturbation is high [70,71] Highly efficient 10 Mobile Information Systems effective adversarial examples. According to [83], it is not easy to detect such adaptive attacks, and some detection techniques effectively work while some ineffective.…”

Section: Detecting Adversarial Examplesmentioning

confidence: 99%

A Review of Deep Learning Security and Privacy Defensive Techniques

Tariq

Memon

Ahmed

et al. 2020

Mobile Information Systems

View full text Add to dashboard Cite

In recent past years, Deep Learning presented an excellent performance in different areas like image recognition, pattern matching, and even in cybersecurity. The Deep Learning has numerous advantages including fast solving complex problems, huge automation, maximum application of unstructured data, ability to give high quality of results, reduction of high costs, no need for data labeling, and identification of complex interactions, but it also has limitations like opaqueness, computationally intensive, need for abundant data, and more complex algorithms. In our daily life, we used many applications that use Deep Learning models to make decisions based on predictions, and if Deep Learning models became the cause of misprediction due to internal/external malicious effects, it may create difficulties in our real life. Furthermore, the Deep Learning training models often have sensitive information of the users and those models should not be vulnerable and expose security and privacy. The algorithms of Deep Learning and machine learning are still vulnerable to different types of security threats and risks. Therefore, it is necessary to call the attention of the industry in respect of security threats and related countermeasures techniques for Deep Learning, which motivated the authors to perform a comprehensive survey of Deep Learning security and privacy security challenges and countermeasures in this paper. We also discussed the open challenges and current issues.

show abstract

“…The bottom line for all defensive approaches is the need for realistic analysis of the potential attackers for goal, knowledge, capability and strategy. Security and Privacy aspects of a machine learning based system have two aspects: safe data and safe model (Liu et al, 2018). The first focuses on the security and privacy issues of the data which is vulnerable against different attacks, more importantly the injection of invalid/malicious input from adversaries or leakage of sensitive information.…”

Section: Robustnessmentioning

confidence: 99%

Establishing a social licence for Financial Technology: Reflections on the role of the private sector in pursuing ethical data practices

et al. 2020

View full text Add to dashboard Cite

Current attention directed at ethical dimensions of data and Artificial Intelligence have led to increasing recognition of the need to secure and maintain public support for uses (and reuses) of people's data. This is essential to establish a "Social Licence" for current and future practices. The notion of a "Social Licence" recognises that there can be meaningful differences between what is legally permissible and what is socially acceptable. Establishing a Social Licence entails public engagement to build relationships of trust and ensure that practices align with public values. While the concept of the Social Licence is well-established in other sectors-notably in relation to extractive industries-it has only very recently begun to be discussed in relation to digital innovation and data-intensive industries. This article therefore draws on existing literature relating to the Social Licence in extractive industries to explore the potential approaches needed to establish a Social Licence for emerging data-intensive industries. Additionally, it draws on well-established literature relating to trust (from psychology and organisational science) to examine the relevance of trust, and trustworthiness, for emerging practices in data-intensive industries. In doing so the article considers the extent to which pursuing a Social Licence might complement regulation and inform codes of practice to place ethical and social considerations at the heart of industry practice. We focus on one key industry: Financial Technology. We demonstrate the importance of combining technical and social approaches to address ethical challenges in data-intensive innovation (particularly relating to Artificial Intelligence) and to establish relationships of trust to underpin a Social Licence for Financial Technology. Such approaches are needed across all areas and industries of data-intensive innovation to complement regulation and inform the development of ethical codes of practice. This is important to underpin culture change and to move beyond rhetorical commitments to develop best practice putting ethics at the heart of innovation.

show abstract

A Survey on Security Threats and Defensive Techniques of Machine Learning: A Data Driven View

Cited by 338 publications

References 62 publications

A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security

A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security

A Review of Deep Learning Security and Privacy Defensive Techniques

Establishing a social licence for Financial Technology: Reflections on the role of the private sector in pursuing ethical data practices

Contact Info

Product

Resources

About