A Survey of Adversarial Learning on Graphs

Chen, Liang; Li, Jintang; Peng, Jiaying; Xie, Tao; Cao, Zhigang; Xu, Kun; He, Xiangnan; Zheng, Zibin

doi:10.48550/arxiv.2003.05730

Cited by 19 publications

(28 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model Attack on Graphs. The adversarial learning [5] benefits the attacks on graphs from examining the robustness of the model via simulating the competitive model or data. On the one hand, the adversarial learning techniques can improve the classification performance like training with adversarial examples [18], which leads the model to learn the embeddings more precisely and robustly.…”

Section: Related Workmentioning

confidence: 99%

NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Data

Hsieh

2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Recent advances in protecting node privacy on graph data and attacking graph neural networks (GNNs) gain much attention. The eye does not bring these two essential tasks together yet. Imagine an adversary can utilize the powerful GNNs to infer users' private labels in a social network. How can we adversarially defend against such privacy attacks while maintaining the utility of perturbed graphs? In this work, we propose a novel research task, adversarial defenses against GNN-based privacy attacks, and present a graph perturbation-based approach, NetFense, to achieve the goal. NetFense can simultaneously keep graph data unnoticeability (i.e., having limited changes on the graph structure), maintain the prediction confidence of targeted label classification (i.e., preserving data utility), and reduce the prediction confidence of private label classification (i.e., protecting the privacy of nodes). Experiments conducted on single-and multiple-target perturbations using three real graph data exhibit that the perturbed graphs by NetFense can effectively maintain data utility (i.e., model unnoticeability) on targeted label classification and significantly decrease the prediction confidence of private label classification (i.e., privacy protection). Extensive studies also bring several insights, such as the flexibility of NetFense, preserving local neighborhoods in data unnoticeability, and better privacy protection for high-degree nodes.

show abstract

Section: Related Workmentioning

confidence: 99%

NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Data

Hsieh

2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…The INSSA follows an adversarial learning approach [14] for risk assessment and anomaly detection. In addition to the node risk scores, the risk of operating in a network environment contributes to the overall network assurance score.…”

Section: Intelligent Network Security State Analysis (Inssa)mentioning

confidence: 99%

Intelligent Zero Trust Architecture for 5G/6G Networks: Principles, Challenges, and the Role of Machine Learning in the context of O-RAN

Ramezanpour¹,

Jagannath²

2021

Preprint

View full text Add to dashboard Cite

In this position paper, we discuss the critical need for integrating zero trust (ZT) principles into next-generation communication networks (5G/6G) for both tactical and commercial applications. We highlight the challenges and introduce the concept of an intelligent zero trust architecture (i-ZTA) as a security framework in 5G/6G networks with untrusted components. While network virtualization, software-defined networking (SDN), and service-based architectures (SBA) are key enablers of 5G networks, operating in an untrusted environment has also become a key feature of the networks. Further, seamless connectivity to a high volume of devices in multi-radio access technology (RAT) has broadened the attack surface on information infrastructure. Network assurance in a dynamic untrusted environment calls for revolutionary architectures beyond existing static security frameworks. This paper presents the architectural design of an i-ZTA upon which modern artificial intelligence (AI) algorithms can be developed to provide information security in untrusted networks. We introduce key ZT principles as real-time Monitoring of the security state of network assets, Evaluating the risk of individual access requests, and Deciding on access authorization using a dynamic trust algorithm, called MED components. The envisioned architecture adopts an SBA-based design, similar to the 3GPP specification of 5G networks, by leveraging the open radio access network (O-RAN) architecture with appropriate real-time engines and network interfaces for collecting necessary machine learning data. The i-ZTA is also expected to exploit the multi-access edge computing (MEC) technology of 5G as a key enabler of intelligent MED components for resource-constraint devices.

show abstract

“…Adversarial learning for networks includes three types of studies: attack, defense, and certifiable robustness [37,21,5]. Adversarial attacks aim to maximally degrade the model performance through perturbing the input data, which includes the modification of node attributes or changes of the network topology.…”

Section: Related Workmentioning

confidence: 99%

Adversarial Robustness of Probabilistic Network Embedding for Link Prediction

Chen

Kang

Lijffijt

et al. 2021

Preprint

View full text Add to dashboard Cite

In today's networked society, many real-world problems can be formalized as predicting links in networks, such as Facebook friendship suggestions, e-commerce recommendations, and the prediction of scientific collaborations in citation networks. Increasingly often, link prediction problem is tackled by means of network embedding methods, owing to their state-of-the-art performance. However, these methods lack transparency when compared to simpler baselines, and as a result their robustness against adversarial attacks is a possible point of concern: could one or a few small adversarial modifications to the network have a large impact on the link prediction performance when using a network embedding model? Prior research has already investigated adversarial robustness for network embedding models, focused on classification at the node and graph level. Robustness with respect to the link prediction downstream task, on the other hand, has been explored much less. This paper contributes to filling this gap, by studying adversarial robustness of Conditional Network Embedding (CNE), a state-of-the-art probabilistic network embedding model, for link prediction. More specifically, given CNE and a network, we measure the sensitivity of the link predictions of the model to small adversarial perturbations of the network, namely changes of the link status of a node pair. Thus, our approach allows one to identify the links and non-links in the network that are most vulnerable to such perturbations, for further investigation by an analyst. We analyze the characteristics of the most and least sensitive perturbations, and empirically confirm that our approach not only succeeds in identifying the most vulnerable links and non-links, but also that it does so in a time-efficient manner thanks to an effective approximation.

show abstract

A Survey of Adversarial Learning on Graphs

Cited by 19 publications

References 65 publications

NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Data

NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Data

Intelligent Zero Trust Architecture for 5G/6G Networks: Principles, Challenges, and the Role of Machine Learning in the context of O-RAN

Adversarial Robustness of Probabilistic Network Embedding for Link Prediction

Contact Info

Product

Resources

About