Author name cluster

Shichun Yang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

NeurIPS Conference 2025 Conference Paper

Versatile Transferable Unlearnable Example Generator

Zhihao Li
Jiale Cai
Gezheng Xu
Hao Zheng
Qiuyue Li
Fan Zhou
Shichun Yang
Charles Ling

The rapid growth of publicly available data has fueled deep learning advancements but also raises concerns about unauthorized data usage. Unlearnable Examples (UEs) have emerged as a data protection strategy that introduces imperceptible perturbations to prevent unauthorized learning. However, most existing UE methods produce perturbations strongly tied to specific training sets, leading to a significant drop in unlearnability when applied to unseen data or tasks. In this paper, we argue that for broad applicability, UEs should maintain their effectiveness across diverse application scenarios. To this end, we conduct the first comprehensive study on the transferability of UEs across diverse and practical yet demanding settings. Specifically, we identify key scenarios that pose significant challenges for existing UE methods, including varying styles, out-of-distribution classes, resolutions, and architectures. Moreover, we propose $\textbf{Versatile Transferable Generator}$ (VTG), a transferable generator designed to safeguard data across various conditions. Specifically, VTG integrates Adversarial Domain Augmentation (ADA) into the generator’s training process to synthesize out-of-distribution samples, thereby improving its generalizability to unseen scenarios. Furthermore, we propose a Perturbation-Label Coupling (PLC) mechanism that leverages contrastive learning to directly align perturbations with class labels. This approach reduces the generator’s reliance on data semantics, allowing VTG to produce unlearnable perturbations in a distribution-agnostic manner. Extensive experiments demonstrate the effectiveness and broad applicability of our approach. Code is available at https: //github. com/zhli-cs/VTG.

PDF Details

AAAI Conference 2024 Conference Paper

Generalizing across Temporal Domains with Koopman Operators

Qiuhao Zeng
Wei Wang
Fan Zhou
Gezheng Xu
Ruizhi Pu
Changjian Shui
Christian Gagné
Shichun Yang

In the field of domain generalization, the task of constructing a predictive model capable of generalizing to a target domain without access to target data remains challenging. This problem becomes further complicated when considering evolving dynamics between domains. While various approaches have been proposed to address this issue, a comprehensive understanding of the underlying generalization theory is still lacking. In this study, we contribute novel theoretic results that aligning conditional distribution leads to the reduction of generalization bounds. Our analysis serves as a key motivation for solving the Temporal Domain Generalization (TDG) problem through the application of Koopman Neural Operators, resulting in Temporal Koopman Networks (TKNets). By employing Koopman Neural Operators, we effectively address the time-evolving distributions encountered in TDG using the principles of Koopman theory, where measurement functions are sought to establish linear transition relations between evolving domains. Through empirical evaluations conducted on synthetic and real-world datasets, we validate the effectiveness of our proposed approach.

PDF Details DOI

EAAI Journal 2024 Journal Article

Multi-order feature interaction-aware intrusion detection scheme for ensuring cyber security of intelligent connected vehicles

Weifeng Gong
Shichun Yang
Haoran Guang
Bin Ma
Bowen Zheng
Yi Shi
Baotian Li
Yaoguang Cao

The evolution of technology has raised concerns regarding cybersecurity for intelligent connected vehicles (ICVs). In-vehicle network in ICVs lacks robust protection mechanisms, making it vulnerable to cyber threats. In response, intrusion detection systems (IDSs) for ICVs have been developed to protect vehicles from malicious cyber attacks. However, current IDS methods solely rely on independent features, limiting their learning capabilities and increasing the number of false detections. Moreover, many IDSs require the knowledge of mapping between network messages and contents, which restricts their application. To address these limitations, we propose the Multi-order Feature Interaction-aware Intrusion Detection (MIFI) scheme for ICVs. Feature attention cross network is designed to address higher-order feature interactions, while factorization machine is used for second-order interactions. Then a discriminator is utilized to detect the attacks. MIFI expands the feature space through features interaction, thereby enhancing its ability to detect attacks. Moreover, it perceives the relationships of vehicle messages, facilitating intrusion detection without knowing the corresponding rules of vehicle messages. The performance of the proposed method is evaluated on two real-vehicle datasets, affirming its effectiveness and robustness. MIFI achieves an accuracy of over 99% in detecting different attacks. The proposed method can improve the accuracy of traditional IDS to a maximum of 99. 99%, and increase the highest F1-score to 97. 18%, demonstrating the model’s ability of achieving multi-order feature interactions. Ultimately, MIFI is suitable for intrusion detection in different types of ICV networks, significantly contributing to the cybersecurity of ICVs.

Details DOI

EAAI Journal 2023 Journal Article

A deep reinforcement learning approach to energy management control with connected information for hybrid electric vehicles

Peng Mei
Hamid Reza Karimi
Hehui Xie
Fei Chen
Cong Huang
Shichun Yang

Considering the importance of the energy management strategy for hybrid electric vehicles, this paper is aiming at addressing the energy optimization control issue using reinforcement learning algorithms. Firstly, this paper establishes a hybrid electric vehicle power system model. Secondly, a hierarchical energy optimization control architecture based on networked information is designed, and a traffic signal timing model is used for vehicle target speed range planning in the upper system. More specifically, the optimal vehicle speed is optimized by a model predictive control algorithm. Thirdly, a mathematical model of vehicle speed variation in connected and unconnected states is established to analyze the effect of vehicle speed planning on fuel economy. Finally, three learning-based energy optimization control strategies, namely Q-learning, deep Q network (DQN), and deep deterministic policy gradient (DDPG) algorithms, are designed under the hierarchical energy optimization control architecture. It is shown that the Q-learning algorithm is able to optimize energy control; however, the agent will meet the ”dimension disaster” once it faces a high-dimensional state space issue. Then, a DQN control strategy is introduced to address the problem. Due to the limitation of the discrete output of DQN, the DDPG algorithm is put forward to achieve continuous action control. In the simulation, the superiority of the DDPG algorithm over Q-learning and DQN algorithms in hybrid electric vehicles is illustrated in terms of its robustness and faster convergence for better energy management purposes.

Details DOI