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

2025-11-10 · Himanshu Pal, Venkata Sai Pranav Bachina, Ankit Gangwal, Charu Sharma 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.

📄 PDF Abstract BibTeX arXiv:2511.07379

Code (0)

등록된 구현이 없습니다.

Tasks

Recommendation Systems Adversarial Defense Anomaly Detection Fraud Detection

LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models

2024-02-18 · Yifan Yang, Jiajun Zhou, Ngai Wong, Zheng Zhang

Various parameter-efficient fine-tuning (PEFT) techniques have been proposed to enable computationally efficient fine-tuning while maintaining model performance. However, existing PEFT methods are still limited by the gr…

Multi-Task Learning parameter-efficient fine-tuning

Training Transitive and Commutative Multimodal Transformers with LoReTTa

2023-05-23 · NeurIPS 2023 11 · Manuel Tran, Yashin Dicente Cid, Amal Lahiani, Fabian J. Theis 외

Training multimodal foundation models is challenging due to the limited availability of multimodal datasets. While many public datasets pair images with text, few combine images with audio or text with audio. Even rarer …

Triplet

Tensor Train Low-rank Approximation (TT-LoRA): Democratizing AI with Accelerated LLMs

2024-08-02 · Afia Anjum, Maksim E. Eren, Ismael Boureima, Boian Alexandrov 외

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing (NLP) tasks, such as question-answering, sentiment analysis, text summarization, …

Machine Translation Model Compression parameter-efficient fine-tuning Question Answering+2

Gray-Box Poisoning of Continuous Malware Ingestion Pipelines

2026-05-06 · Jan Dolejš, Martin Jureček, Róbert Lórencz arxiv

Modern malware detection pipelines rely on continuous data ingestion and machine learning to counter the high volume of novel threats. This work investigates a realistic gray-box poisoning threat model targeting these pi…

Malware Detection

Temporal Robustness against Data Poisoning

2023-02-07 · NeurIPS 2023 11 · Wenxiao Wang, Soheil Feizi

Data poisoning considers cases when an adversary manipulates the behavior of machine learning algorithms through malicious training data. Existing threat models of data poisoning center around a single metric, the number…

Data Poisoning