Towards Secrecy-Aware Attacks Against Trust Prediction in Signed Social Networks

TL;DR

This paper explores how attackers can manipulate signed social networks to deceive trust prediction models, proposing secrecy-aware poisoning attacks that evade detection while maintaining effectiveness, thereby revealing practical security threats.

Contribution

It introduces novel secrecy-aware poisoning attack methods against trust prediction in signed networks, combining bi-level optimization with detection evasion techniques, advancing understanding of realistic attack scenarios.

Findings

Basic attacks severely disrupt trust prediction accuracy.

Refined attacks evade detection with minimal performance loss.

Attacks demonstrate significant threat to trust prediction systems.

Abstract

Signed social networks are widely used to model the trust relationships among online users in security-sensitive systems such as cryptocurrency trading platforms, where trust prediction plays a critical role. In this paper, we investigate how attackers could mislead trust prediction by secretly manipulating signed networks. To this end, we first design effective poisoning attacks against representative trust prediction models. The attacks are formulated as hard bi-level optimization problems, for which we propose several efficient approximation solutions. However, the resulting basic attacks would severely change the structural semantics (in particular, both local and global balance properties) of a signed network, which makes the attacks prone to be detected by the powerful attack detectors we designed. Given this, we further refine the basic attacks by integrating some conflicting metrics as penalty terms into the objective function. The refined attacks become secrecy-aware, i.e., they can successfully evade attack detectors with high probability while sacrificing little attack performance. We conduct comprehensive experiments to demonstrate that the basic attacks can severely disrupt trust prediction but could be easily detected, and the refined attacks perform almost equally well while evading detection. Overall, our results significantly advance the knowledge in designing more practical attacks, reflecting more realistic threats to current trust prediction models. Moreover, the results also provide valuable insights and guidance for building up robust trust prediction systems.