1

Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series Forecasting

Irregular multivariate time series (IMTS), characterized by uneven sampling and inter-variate asynchrony, fuel many forecasting …

Ziyu Zhou, Yiming Huang, Yanyun Wang, Yuankai Wu, James Kwok, Yuxuan Liang

Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data

Synthetic data refers to artificial samples generated by models. While it has been validated to significantly enhance the performance …

Zi Liang, Qingqing Ye, Xuan Liu, Yanyun Wang, Jianliang Xu, Haibo Hu

BackdoorDM: A Comprehensive Benchmark for Backdoor Learning in Diffusion Model

Backdoor learning is a critical research topic for understanding the vulnerabilities of deep neural networks. While it has been …

Weilin Lin, Nanjun Zhou, Yanyun Wang, Jianze Li, Hui Xiong, Li Liu

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training

Adversarial Training (AT) is one of the most effective methods to train robust Deep Neural Networks (DNNs). However, AT creates an …

Yanyun Wang, Li Liu

"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced Distillation

Model extraction attacks (MEAs) on large language models (LLMs) have received increasing attention in recent research. However, …

Zi Liang, Qingqing Ye, Yanyun Wang, Sen Zhang, Yaxin Xiao, Ronghua Li, Jianliang Xu, Haibo Hu

TSFool: Crafting Highly-Imperceptible Adversarial Time Series Through Multi-Objective Attack

Recent years have witnessed the success of recurrent neural network (RNN) models in time series classification (TSC). However, neural …

Yanyun Wang, Dehui Du, Haibo Hu, Zi Liang, Yuanhao Liu

Meta Pattern Concern Score: A Novel Evaluation Measure with Human Values for Multi-classifiers

While advanced classifiers have been increasingly used in real-world safety-critical applications, how to properly evaluate the …

Yanyun Wang, Dehui Du, Yuanhao Liu

Efficient Adversarial Sequence Generation for RNN with Symbolic Weighted Finite Automata

Adversarial sequence generation plays an important role in improving the robustness of Recurrent Neural Networks (RNNs). However, there …

Mingjun Ma, Dehui Du, Yuanhao Liu, Yanyun Wang, Yiyang Li