# Target Defense Against Link-Prediction-Based Attacks via Evolutionary Perturbations

arXiv: https://arxiv.org/abs/1809.05912 · HTML: https://mlsanity.com/paper/1809.05912/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2018.

## Built on by (most cited first, 7 of 7)

- [GANI: Global Attacks on Graph Neural Networks via Imperceptible Node Injections](https://mlsanity.com/paper/2210.12598/) (2022)
- [Time-aware Metapath Feature Augmentation for Ponzi Detection in Ethereum](https://mlsanity.com/paper/2210.16863/) (2022)
- [Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning](https://mlsanity.com/paper/2305.02901/) (2023)
- [Adversarial Robustness of Probabilistic Network Embedding for Link Prediction](https://mlsanity.com/paper/2107.01936/) (2021)
- [GGT: Graph-Guided Testing for Adversarial Sample Detection of Deep Neural Network](https://mlsanity.com/paper/2107.07043/) (2021)
- [Large-Scale Privacy-Preserving Network Embedding against Private Link Inference Attacks](https://mlsanity.com/paper/2205.14440/) (2022)
- [A Federated Parameter Aggregation Method for Node Classification Tasks with Different Graph Network Structures](https://mlsanity.com/paper/2403.16004/) (2024)

## Abstract (arXiv)

In social networks, by removing some target-sensitive links, privacy protection might be achieved. However, some hidden links can still be re-observed by link prediction methods on observable networks. In this paper, the conventional link prediction method named Resource Allocation Index (RA) is adopted for privacy attacks. Several defense methods are proposed, including heuristic and evolutionary approaches, to protect targeted links from RA attacks via evolutionary perturbations. This is the first time to study privacy protection on targeted links against link-prediction-based attacks. Some links are randomly selected from the network as targeted links for experimentation. The simulation results on six real-world networks demonstrate the superiority of the evolutionary perturbation approach for target defense against RA attacks. Moreover, transferring experiments show that, although the evolutionary perturbation approach is designed to against RA attacks, it is also effective against other link-prediction-based attacks.