Kai Chen

Kai Chen

Auto-generated profile, based on publicly available information

Kai Chen

Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
28 December 2017 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
Jing ChenJing Chen
Jing Chen
CWChiheng Wang
Chiheng Wang
ZZZiming Zhao
Ziming Zhao
KCKai Chen
Kai Chen
RDRuiying Du
Ruiying Du
GAGail-Joon Ahn
Gail-Joon Ahn
In recent years, we witnessed a drastic increase of ransomware, especially on popular mobile platforms including Android. Ransomware extorts victims for a sum of money by taking control of their devices or files. In light of their rapid growth, there is a pressing need to develop effective countermeasure solutions. However, the research community is still constrained by the lack of a comprehensive data set, and there exists no insightful understanding of mobile ransomware in the wild. In this paper, we focus on the Android platform and aim to characterize existing Android ransomware. Specifically, we have managed to collect 2,721 ransomware samples that cover the majority of existing Android ransomware families. Based on these samples, we systematically characterize them from several aspects, including timeline and malicious features. In addition, the detection results of existing anti-virus tools are rather disappointing, which clearly calls for customized anti-mobile-ransomware solutions. To detect ransomware that extorts users by encrypting data, we propose a novel real-time detection system, called RansomProber. By analyzing the user interface widgets of related activities and the coordinates of users' finger movements, RansomProber can infer whether the file encryption operations are initiated by users. The experimental results show that RansomProber can effectively detect encrypting ransomware with high accuracy and acceptable runtime performance.

9 November 2020 in IEEE Transactions on Software Engineering
Verified
Journal Article
Closed access
YHYingzhe He
Yingzhe He
GMGuozhu Meng
Guozhu Meng
KCKai Chen
Kai Chen
XHXingbo Hu
Xingbo Hu
JHJinwen He
Jinwen He
Deep learning has gained tremendous success and great popularity in the past few years. However, deep learning systems are suffering several inherent weaknesses, which can threaten the security of learning models. Deep learning's wide use further magnifies the impact and consequences. To this end, lots of research has been conducted with the purpose of exhaustively identifying intrinsic weaknesses and subsequently proposing feasible mitigation. Yet few are clear about how these weaknesses are incurred and how effective these attack approaches are in assaulting deep learning. In order to unveil the security weaknesses and aid in the development of a robust deep learning system, we undertake an investigation on attacks towards deep learning, and analyze these attacks to conclude some findings in multiple views. In particular, we focus on four types of attacks associated with security threats of deep learning: model extraction attack, model inversion attack, poisoning attack and adversarial attack. For each type of attack, we construct its essential workflow as well as adversary capabilities and attack goals. Pivot metrics are devised for comparing the attack approaches, by which we perform quantitative and qualitative analyses. From the analysis, we have identified significant and indispensable factors in an attack vector, e.g., how to reduce queries to target models, what distance should be used for measuring perturbation. We shed light on 18 findings covering these approaches' merits and demerits, success probability, deployment complexity and prospects. Moreover, we discuss other potential security weaknesses and possible mitigation which can inspire relevant research in this area.

6 February 2023 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
PLPeizhuo Lv
Peizhuo Lv
PLPan Li
Pan Li
SZShengzhi Zhang
Shengzhi Zhang
KCKai Chen
Kai Chen
RLRuigang Liang
Ruigang Liang
YLYingjiu Li
Yingjiu Li
Recently, stealing highly-valuable and large-scale deep neural network (DNN) models becomes pervasive. The stolen models may be re-commercialized, e.g., deployed in embedded devices, released in model markets, utilized in competitions, etc, which infringes the Intellectual Property (IP) of the original owner. Detecting IP infringement of the stolen models is quite challenging, even with the white-box access to them in the above scenarios, since they may have experienced fine-tuning, pruning, functionality-equivalent adjustment to destruct any embedded watermark. Furthermore, the adversaries may also attempt to extract the embedded watermark or forge a similar watermark to falsely claim ownership. In this paper, we propose a novel DNN watermarking solution, named $HufuNet$ , to detect IP infringement of DNN models against the above mentioned attacks. Furthermore, HufuNet is the first one theoretically proved to guarantee robustness against fine-tuning attacks. We evaluate HufuNet rigorously on four benchmark datasets with five popular DNN models, including convolutional neural network (CNN) and recurrent neural network (RNN). The experiments and analysis demonstrate that HufuNet is highly robust against model fine-tuning/pruning, transfer learning, kernels cutoff/supplement, functionality-equivalent attacks and fraudulent ownership claims, thus highly promising to protect large-scale DNN models in the real world.

31 August 2018 in Cybersecurity
Verified
Journal Article
Open access
PDF file
QZQianqian Zhao
Qianqian Zhao
KCKai Chen
Kai Chen
TLTongxin Li
Tongxin Li
YYYi Yang
Yi Yang
XWXiaoFeng Wang
XiaoFeng Wang
Telecommunication fraud has continuously been causing severe financial loss to telecommunication customers in China for several years. Traditional approaches to detect telecommunication frauds usually rely on constructing a blacklist of fraud telephone numbers. However, attackers can simply evade such detection by changing their numbers, which is very easy to achieve through VoIP (Voice over IP). To solve this problem, we detect telecommunication frauds from the contents of a call instead of simply through the caller’s telephone number. Particularly, we collect descriptions of telecommunication fraud from news reports and social media. We use machine learning algorithms to analyze data and to select the high-quality descriptions from the data collected previously to construct datasets. Then we leverage natural language processing to extract features from the textual data. After that, we build rules to identify similar contents within the same call for further telecommunication fraud detection. To achieve online detection of telecommunication frauds, we develop an Android application which can be installed on a customer’s smartphone. When an incoming fraud call is answered, the application can dynamically analyze the contents of the call in order to identify frauds. Our results show that we can protect customers effectively.

17 November 2021 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
JGJiqiang Gao
Jiqiang Gao
BHBoyu Hou
Boyu Hou
XGXiaojie Guo
Xiaojie Guo
Zheli LiuZheli Liu
Zheli Liu
YZYing Zhang
Ying Zhang
JLJin Li
Jin Li
Federated learning allows a large number of resource-constrained clients to train a globally-shared model together without sharing local data. These clients usually have only a few classes (categories) of data for training, where the data distribution is non-iid (not independent identically distributed). In this paper, we put forward the concept of category privacy for the first time to indicate which classes of data a client has, which is an important but ignored privacy goal in the federated learning with non-iid data. Although secure aggregation protocols are designed for federated learning to protect the input privacy of clients, we perform the first systematic study on category inference attack and demonstrate that these protocols cannot fully protect category privacy. We design a differential selection strategy and two de-noising approaches to achieve the attack goal successfully. In our evaluation, we apply the attack to non-iid federated learning settings with various datasets. On MNIST, CIFAR-10, AG\_news, and DBPedia datasets, our attack achieves >90% accuracy measured in F1-score in most cases. We further consider a possible detection method and propose two strategies to make the attack more inconspicuous.

2 December 2024
Verified
Conference Paper
Open access
TLTong Liu
Tong Liu
ZDZizhuang Deng
Zizhuang Deng
GMGuozhu Meng
Guozhu Meng
Yuekang LiYuekang Li
Yuekang Li
KCKai Chen
Kai Chen
Large Language Models (LLMs) show promise in transforming software development, with a growing interest in integrating them into more intelligent apps. Frameworks like LangChain aid LLM-integrated app development, offering code execution utility/APIs for custom actions. However, these capabilities theoretically introduce Remote Code Execution (RCE) vulnerabilities, enabling remote code execution through prompt injections. No prior research systematically investigates these frameworks' RCE vulnerabilities or their impact on applications and exploitation consequences. Therefore, there is a huge research gap in this field. In this study, we propose LLMSmith to detect, validate and exploit the RCE vulnerabilities in LLM-integrated frameworks and apps. To achieve this goal, we develop two novel techniques, including 1) a lightweight static analysis to construct call chains to identify RCE vulnerabilities in frameworks; 2) a systematical prompt-based exploitation method to verify and exploit the found vulnerabilities in LLM-integrated apps. This technique involves various strategies to control LLM outputs, trigger RCE vulnerabilities and launch subsequent attacks. Our research has uncovered a total of 20 vulnerabilities in 11 LLM-integrated frameworks, comprising 19 RCE vulnerabilities and 1 arbitrary file read/write vulnerability. Of these, 17 have been confirmed by the framework developers, with 13 vulnerabilities being assigned CVE IDs, 6 of which have a CVSS score of 9.8, and we were also awarded a bug bounty of 1350. For the 51 apps potentially affected by RCE, we successfully executed attacks on 17 apps, 16 of which are vulnerable to RCE and 1 to SQL injection. Furthermore, we conduct a comprehensive analysis of these vulnerabilities and construct practical attacks to demonstrate the hazards in reality, e.g., app output hijacking, user data leakage, even the potential to take full control of systems. Last, we propose several mitigation measures for both framework and app developers to counteract such attacks.