Kangjie Chen

Kangjie Chen

Auto-generated profile, based on publicly available information

Kangjie Chen

Nanyang Technological University Singapore

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2021 in IEEE Transactions on Smart Grid
Verified
Journal Article
Closed access
YZYan Zheng
Yan Zheng
ZYZiming Yan
Ziming Yan
KCKangjie Chen
Kangjie Chen
JSJianwen Sun
Jianwen Sun
Yan XuYan Xu
Yan Xu
YLYang Liu
Yang Liu
This paper studies the vulnerability of deep reinforcement learning (DRL) models for power systems topology optimization under data perturbations and cyber-attack. DRL has recently solved many complex power system optimization problems. However, it has been practically proven that small perturbations of input data can lead to drastically different control decisions and induce danger. To evaluate and mitigate the security risks of DRL models in power systems, we propose a vulnerability assessment method for such DRL models under noisy data and cyber-attack. In specific, we assess the vulnerability of a DRL model in a way that perturbations are constructed to minimize the model's performance. Besides, several vulnerability indices are proposed to identify the characteristics of perturbations that may cause malfunction of DRL. Simulations on the 14-bus system and the IEEE 118-bus system for topology optimization are carried out to validate the effectiveness of the proposed vulnerability assessment method. The results show that the performance of DRL models for power systems can be significantly degraded under cyber-attack and data perturbations, especially when a proposed vulnerability index has abnormal values.

17 April 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
RLRenyang Liu
Renyang Liu
WZWei Zhou
Wei Zhou
TZTianwei Zhang
Tianwei Zhang
KCKangjie Chen
Kangjie Chen
Jun ZhaoJun Zhao
Jun Zhao
KLKwok-Yan Lam
Kwok-Yan Lam
Existing black-box attacks have demonstrated promising potential in creating adversarial examples (AE) to deceive deep learning models. Most of these attacks need to handle a vast optimization space and require a large number of queries, hence exhibiting limited practical impacts in real-world scenarios. In this paper, we propose a novel black-box attack strategy, Conditional Diffusion Model Attack (CDMA), to improve the query efficiency of generating AEs under query-limited situations. The key insight of CDMA is to formulate the task of AE synthesis as a distribution transformation problem, i.e., benign examples and their corresponding AEs can be regarded as coming from two distinctive distributions and can transform from each other with a particular converter. Unlike the conventional query-and-optimization approach, we generate eligible AEs with direct conditional transform using the aforementioned data converter, which can significantly reduce the number of queries needed. CDMA adopts the conditional Denoising Diffusion Probabilistic Model as the converter, which can learn the transformation from clean samples to AEs, and ensure the smooth development of perturbed noise resistant to various defense strategies. We demonstrate the effectiveness and efficiency of CDMA by comparing it with nine state-of-the-art black-box attacks across three benchmark datasets. On average, CDMA can reduce the query count to a handful of times; in most cases, the query count is only ONE. We also show that CDMA can obtain > 99% attack success rate for untargeted attacks over all datasets and targeted attack over CIFAR-10 with the noise budget of ϵ = 16.

28 October 2024
Verified
Conference Paper
Open access
HWHao Wang
Hao Wang
SGShangwei Guo
Shangwei Guo
JHJialing He
Jialing He
KCKangjie Chen
Kangjie Chen
SZShudong Zhang
Shudong Zhang
TXTao Xiang
Tao Xiang
Text-to-image (T2I) diffusion models enjoy great popularity and many individuals and companies build their applications based on publicly released T2I diffusion models. Previous studies have demonstrated that backdoor attacks can elicit T2I diffusion models to generate unsafe target images through textual triggers. However, existing backdoor attacks typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance of T2I diffusion models. To address these issues, we propose EvilEdit, a training-free and data-free backdoor attack against T2I diffusion models. EvilEdit directly edits the projection matrices in the cross-attention layers to achieve projection alignment between a trigger and the corresponding backdoor target. We preserve the functionality of the backdoored model using a protected whitelist to ensure the semantic of non-trigger words is not accidentally altered by the backdoor. We also propose a visual target attack EvilEdit VTA, enabling adversaries to use specific images as backdoor targets. We conduct empirical experiments on Stable Diffusion and the results demonstrate that the EvilEdit can backdoor T2I diffusion models within one second with up to 100% success rate. Furthermore, our EvilEdit modifies only 2.2% of the parameters and maintains the model's performance on benign prompts. Our code is available at https://github.com/haowang-cqu/EvilEdit.

1 January 2013 in Molecular Cancer Therapeutics
Verified
Journal Article
Open access
PDF file
CXChunyang Xing
Chunyang Xing
WZWuhua Zhou
Wuhua Zhou
SDSongming Ding
Songming Ding
HXHaiyang Xie
Haiyang Xie
WZWu Zhang
Wu Zhang
LZLin Zhou
Lin Zhou
It has been shown that Ring finger protein 43 (RNF43) is overexpressed in colorectal cancer and mediates cancer cell proliferation; however, its role in hepatocellular carcinoma (HCC) remains unknown. In this study, we found that RNF43 was frequently overexpressed in HCCs, and this overexpression was correlated with positive vascular invasion, poor tumor differentiation, and advanced tumor stage. Functional studies showed that knockdown of RNF43 could induce apoptosis and inhibit proliferation, invasion, colony formation, and xenograft growth of HCCs. Microarray-based gene profiling showed a total of 229 genes differentially expressed after RNF43 knockdown, many of which are involved in oncogenic processes such as cell proliferation, cell adhesion, cell motility, cell death, DNA repair, and so on. These results suggest that RNF43 is involved in tumorigenesis and progression of HCCs and that antagonism of RNF43 may be beneficial for HCC treatment. Mol Cancer Ther; 12(1); 94–103. ©2012 AACR.

4 December 2023 in arXiv
Verified
Preprint
Open access
PDF file
GLGuanlin Li
Guanlin Li
KCKangjie Chen
Kangjie Chen
YXYuan Xu
Yuan Xu
HQHan Qiu
Han Qiu
TZTianwei Zhang
Tianwei Zhang
Adversarial training is an important topic in robust deep learning, but the community lacks attention to its practical usage. In this paper, we aim to resolve a real-world challenge, i.e., training a model on an imbalanced and noisy dataset to achieve high clean accuracy and adversarial robustness, with our proposed Omnipotent Adversarial Training (OAT) strategy. OAT consists of two innovative methodologies to address the imperfection in the training set. We first introduce an oracle into the adversarial training process to help the model learn a correct data-label conditional distribution. This carefully-designed oracle can provide correct label annotations for adversarial training. We further propose logits adjustment adversarial training to overcome the data imbalance issue, which can help the model learn a Bayes-optimal distribution. Our comprehensive evaluation results show that OAT outperforms other baselines by more than 20% clean accuracy improvement and 10% robust accuracy improvement under complex combinations of data imbalance and label noise scenarios. The code can be found in https://github.com/GuanlinLee/OAT.

28 November 2022
Verified
Book Chapter
Closed access
PDF file
KCKangjie Chen
Kangjie Chen