# LoReTTA: A Low Resource Framework To Poison Continuous Time Dynamic Graphs

arXiv: https://arxiv.org/abs/2511.07379 · HTML: https://mlsanity.com/paper/2511.07379/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 10 Nov 2025.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (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)
- [Graph Neural Network for Traffic Forecasting: A Survey](https://mlsanity.com/paper/2101.11174/) (2021)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [Do We Really Need Complicated Model Architectures For Temporal Networks?](https://mlsanity.com/paper/2302.11636/) (2023)
- [Adversarial Attacks on Node Embeddings via Graph Poisoning](https://mlsanity.com/paper/1809.01093/) (2018)
- [Streaming Graph Neural Networks](https://mlsanity.com/paper/1810.10627/) (2018)
- [Temporal Knowledge Graph Completion: A Survey](https://mlsanity.com/paper/2201.08236/) (2022)
- [Dynamic Graph Representation Learning via Self-Attention Networks](https://mlsanity.com/paper/1812.09430/) (2018)
- [F-FADE: Frequency Factorization for Anomaly Detection in Edge Streams](https://mlsanity.com/paper/2011.04723/) (2020)
- [Adversarial Attack on Community Detection by Hiding Individuals](https://mlsanity.com/paper/2001.07933/) (2020)
- [Decoupled Graph Neural Networks for Large Dynamic Graphs](https://mlsanity.com/paper/2305.08273/) (2023)
- [Time-aware Gradient Attack on Dynamic Network Link Prediction](https://mlsanity.com/paper/1911.10561/) (2019)
- [Sketch-Based Anomaly Detection in Streaming Graphs](https://mlsanity.com/paper/2106.04486/) (2021)
- [Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs](https://mlsanity.com/paper/2308.10779/) (2023)
- [Structack: Structure-based Adversarial Attacks on Graph Neural Networks](https://mlsanity.com/paper/2107.11327/) (2021)

## Abstract (arXiv)

Temporal Graph Neural Networks (TGNNs) are increasingly used in high-stakes domains, such as financial forecasting, recommendation systems, and fraud detection. However, their susceptibility to poisoning attacks poses a critical security risk. We introduce LoReTTA (Low Resource Two-phase Temporal Attack), a novel adversarial framework on Continuous-Time Dynamic Graphs, which degrades TGNN performance by an average of 29.47% across 4 widely benchmark datasets and 4 State-of-the-Art (SotA) models. LoReTTA operates through a two-stage approach: (1) sparsify the graph by removing high-impact edges using any of the 16 tested temporal importance metrics, (2) strategically replace removed edges with adversarial negatives via LoReTTA's novel degree-preserving negative sampling algorithm. Our plug-and-play design eliminates the need for expensive surrogate models while adhering to realistic unnoticeability constraints. LoReTTA degrades performance by upto 42.0% on MOOC, 31.5% on Wikipedia, 28.8% on UCI, and 15.6% on Enron. LoReTTA outperforms 11 attack baselines, remains undetectable to 4 leading anomaly detection systems, and is robust to 4 SotA adversarial defense training methods, establishing its effectiveness, unnoticeability, and robustness.