mlsanityData to 14 Oct 2026

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

arXiv 2511.07379 ↗First posted 10 Nov 2025cs.LG cs.AIcited by 0

Not on the map. Why?

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.

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

25 of 42 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  4. 2019Graph Neural Networks for Social Recommendationcited by 714
  5. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
  6. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
  7. 2020Inductive Representation Learning on Temporal Graphscited by 462
  8. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 448
  9. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 447
  10. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
  11. 2018Adversarial Attack on Graph Structured Datacited by 301
  12. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 261
13 more
  1. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  2. 2023Do We Really Need Complicated Model Architectures For Temporal Networks?cited by 143
  3. 2018Adversarial Attacks on Node Embeddings via Graph Poisoningcited by 109
  4. 2018Streaming Graph Neural Networkscited by 91
  5. 2022Temporal Knowledge Graph Completion: A Surveycited by 61
  6. 2018Dynamic Graph Representation Learning via Self-Attention Networkscited by 39
  7. 2020F-FADE: Frequency Factorization for Anomaly Detection in Edge Streamscited by 26
  8. 2020Adversarial Attack on Community Detection by Hiding Individualscited by 20
  9. 2023Decoupled Graph Neural Networks for Large Dynamic Graphscited by 14
  10. 2019Time-aware Gradient Attack on Dynamic Network Link Predictioncited by 10
  11. 2021Sketch-Based Anomaly Detection in Streaming Graphscited by 9
  12. 2023Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphscited by 9
  13. 2021Structack: Structure-based Adversarial Attacks on Graph Neural Networkscited by 8

Built on by

Not cited yet.