# On Measuring Unnoticeability of Graph Adversarial Attacks: Observations, New Measure, and Applications

arXiv: https://arxiv.org/abs/2501.05015 · HTML: https://mlsanity.com/paper/2501.05015/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 9 Jan 2025.

## Builds on (most cited first, 25 of 25)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [Adversarial Attack on Graph Structured Data](https://mlsanity.com/paper/1806.02371/) (2018)
- [Adversarial Attacks on Graph Neural Networks via Meta Learning](https://mlsanity.com/paper/1902.08412/) (2019)
- [Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective](https://mlsanity.com/paper/1906.04214/) (2019)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [Adversarial Attack and Defense on Graph Data: A Survey](https://mlsanity.com/paper/1812.10528/) (2018)
- [Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models](https://mlsanity.com/paper/2005.07959/) (2020)
- [Hiding Individuals and Communities in a Social Network](https://mlsanity.com/paper/1608.00375/) (2016)
- [Towards More Practical Adversarial Attacks on Graph Neural Networks](https://mlsanity.com/paper/2006.05057/) (2020)
- [Understanding and Improving Graph Injection Attack by Promoting Unnoticeability](https://mlsanity.com/paper/2202.08057/) (2022)
- [Single Node Injection Attack against Graph Neural Networks](https://mlsanity.com/paper/2108.13049/) (2021)
- [Are Defenses for Graph Neural Networks Robust?](https://mlsanity.com/paper/2301.13694/) (2023)
- [Understanding Structural Vulnerability in Graph Convolutional Networks](https://mlsanity.com/paper/2108.06280/) (2021)
- [OpenGSL: A Comprehensive Benchmark for Graph Structure Learning](https://mlsanity.com/paper/2306.10280/) (2023)
- [Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs](https://mlsanity.com/paper/2206.09144/) (2022)
- [Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks](https://mlsanity.com/paper/2002.08012/) (2020)

## Built on by (most cited first, 1 of 1)

- [TiGer: Self-Supervised Purification for Time-evolving Graphs](https://mlsanity.com/paper/2503.06990/) (2025)

## Abstract (arXiv)

Adversarial attacks are allegedly unnoticeable. Prior studies have designed attack noticeability measures on graphs, primarily using statistical tests to compare the topology of original and (possibly) attacked graphs. However, we observe two critical limitations in the existing measures. First, because the measures rely on simple rules, attackers can readily enhance their attacks to bypass them, reducing their attack "noticeability" and, yet, maintaining their attack performance. Second, because the measures naively leverage global statistics, such as degree distributions, they may entirely overlook attacks until severe perturbations occur, letting the attacks be almost "totally unnoticeable." To address the limitations, we introduce HideNSeek, a learnable measure for graph attack noticeability. First, to mitigate the bypass problem, HideNSeek learns to distinguish the original and (potential) attack edges using a learnable edge scorer (LEO), which scores each edge on its likelihood of being an attack. Second, to mitigate the overlooking problem, HideNSeek conducts imbalance-aware aggregation of all the edge scores to obtain the final noticeability score. Using six real-world graphs, we empirically demonstrate that HideNSeek effectively alleviates the observed limitations, and LEO (i.e., our learnable edge scorer) outperforms eleven competitors in distinguishing attack edges under five different attack methods. For an additional application, we show that LEO boost the performance of robust GNNs by removing attack-like edges.