Adversarial Attack against Cross-lingual Knowledge Graph Alignment

Abstract

Recent literatures have shown that knowledge graph (KG) learning models are highly vulnerable to adversarial attacks. However, there is still a paucity of vulnerability analyses of cross-lingual entity alignment under adversarial attacks. This paper proposes an adversarial attack model with two novel attack techniques to perturb the KG structure and degrade the quality of deep cross-lingual entity alignment. First, an entity density maximization method is employed to hide the attacked entities in dense regions in two KGs, such that the derived perturbations are unnoticeable. Second, an attack signal amplification method is developed to reduce the gradient vanishing issues in the process of adversarial attacks for further improving the attack effectiveness.

Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing

“…Fair Classification. Trustworthy machine learning has attracted active research in recent years (Palanisamy et al, 2018;Lei et al, 2019;Zhou et al, 2020;Zhang et al, 2020b;Zhou & Liu, 2019;Wu et al, 2021;Zhou et al, 2021b;Zhao et al, 2021;Ren et al, 2021; Ma et al, 2021;Zhang et al, 2021). Fair classification techniques aim to guarantee the learnt classifiers that are not only accurate but also fair with respect to sensitive attributes (Caton & Haas, 2020;Mehrabi et al, 2021).…”