TY - GEN
T1 - ADMIRING
T2 - 19th IEEE International Conference on Data Mining, ICDM 2019
AU - Zhou, Qinghai
AU - Li, Liangyue
AU - Cao, Nan
AU - Ying, Lei
AU - Tong, Hanghang
N1 - Funding Information:
This work is supported by NSF (IIS-1651203, IIS-1715385), DHS (2017-ST-061-QA0001) and Fundamental Research Funds for the Central Universities.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Multi-sourced networks naturally appear in many application domains, ranging from bioinformatics, social networks, neuroscience to management. Although state-of-the-art offers rich models and algorithms to find various patterns when input networks are given, it has largely remained nascent on how vulnerable the mining results are due to the adversarial attacks. In this paper, we address the problem of attacking multi-network mining through the way of deliberately perturbing the networks to alter the mining results. The key idea of the proposed method (Admiring) is effective influence functions on the Sylvester equation defined over the input networks, which plays a central and unifying role in various multi-network mining tasks. The proposed algorithms bear two main advantages, including (1) effectiveness, being able to accurately quantify the rate of change of the mining results in response to attacks; and (2) generality, being applicable to a variety of multi-network mining tasks ( e.g., graph kernel, network alignment, cross-network node similarity) with different attacking strategies (e.g., edge/node removal, attribute alteration).
AB - Multi-sourced networks naturally appear in many application domains, ranging from bioinformatics, social networks, neuroscience to management. Although state-of-the-art offers rich models and algorithms to find various patterns when input networks are given, it has largely remained nascent on how vulnerable the mining results are due to the adversarial attacks. In this paper, we address the problem of attacking multi-network mining through the way of deliberately perturbing the networks to alter the mining results. The key idea of the proposed method (Admiring) is effective influence functions on the Sylvester equation defined over the input networks, which plays a central and unifying role in various multi-network mining tasks. The proposed algorithms bear two main advantages, including (1) effectiveness, being able to accurately quantify the rate of change of the mining results in response to attacks; and (2) generality, being applicable to a variety of multi-network mining tasks ( e.g., graph kernel, network alignment, cross-network node similarity) with different attacking strategies (e.g., edge/node removal, attribute alteration).
KW - Adversarial attacks
KW - Multi network mining
KW - Sylvester Equation
UR - http://www.scopus.com/inward/record.url?scp=85078920002&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078920002&partnerID=8YFLogxK
U2 - 10.1109/ICDM.2019.00201
DO - 10.1109/ICDM.2019.00201
M3 - Conference contribution
AN - SCOPUS:85078920002
T3 - Proceedings - IEEE International Conference on Data Mining, ICDM
SP - 1522
EP - 1527
BT - Proceedings - 19th IEEE International Conference on Data Mining, ICDM 2019
A2 - Wang, Jianyong
A2 - Shim, Kyuseok
A2 - Wu, Xindong
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 8 November 2019 through 11 November 2019
ER -