Research map / Adversarial robustness and security / Attacks on text and graphs
LORETTA: A Low Resource Framework to Poison Continuous Time Dynamic Graphs
Himanshu Pal, Venkata Sai Pranav Bachina, Ankit Gangwal, Charu Sharma
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| apply LoReTTA attack to TGN with a defense: cosine filtering | TGN under LoReTTA-Degree · Wikipedia, p=0.3 | MRR (%): clean 80.50 -> 27.57 with cosine filtering defense | Hurt |
| increase attacker knowledge of training data from 0.2 to 0.8 for degree/pagerank removal (ablation) | LoReTTA sparsification · Wikipedia, TGN | MRR (%): Degree 60.78 -> 67.06; Pagerank 61.18 -> 67.40 | Hurt |
| increase attacker knowledge for cosine removal (ablation) | LoReTTA sparsification · Wikipedia, TGN | MRR (%): 57.16 -> 58.25 | No clear effect |
| increase attacker knowledge for random removal (ablation) | Random removal · Wikipedia, TGN | MRR (%): 62.61 -> 62.61 | No clear effect |
| raise perturbation rate p (ablation) | LoReTTA vs T-spear · Wikipedia, TGN | MRR (%) | Improved |
Closest papers by meaning
- Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs (AAAI 2024 · similarity 0.89)
- MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future Knowledge (ICML 2025 · similarity 0.88)
- Temporal-Aware Evaluation and Learning for Temporal Graph Neural Networks (AAAI 2025 · similarity 0.86)
- Value at Adversarial Risk: A Graph Defense Strategy against Cost-Aware Attacks (AAAI 2024 · similarity 0.85)
- A Simple and Yet Fairly Effective Defense for Graph Neural Networks (AAAI 2024 · similarity 0.84)
- Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
