Qiang Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Qiang Li has a total of 89 co-authors. Here are the top co-authors by number of shared publications:
Limin Sun
Institute of Information Engineering–Chinese Academy of Sciences (CAS), Beijing, China
19 shared publicationsXuan Feng
School of Cyber Security, University of Chinese Academy of Sciences, China. and also with the Beijing Key Laboratory of IOT Information Security Technology, Institute of Information Engineering, CAS, China
8 shared publicationsHaining Wang
7 shared publications- Haining Wang
Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA
7 shared publications - Jiqiang Liu
Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing 100044, China
5 shared publications - Limin Sun
Chinese Academy of Sciences
5 shared publications
Latest Publications
- Open Access
Automatically Generating Rules of Malicious Software Packages via Large Language Model
Today's security tools predominantly rely on predefined rules crafted by experts, making them poorly adapted to the emergence of software supply chain attacks. To tackle this limitation, we propose a novel tool, RuleLLM, which leverages large language models (LLMs) to automate rule generation for OSS ecosystems. RuleLLM extracts metadata and code snippets from malware as its input, producing YARA and Semgrep rules that can be directly deployed in software development. Specifically, the rule generation task involves three subtasks: crafting rules, refining rules, and aligning rules. To validate RuleLLM's effectiveness, we implemented a prototype system and conducted experiments on the dataset of 1,633 malicious packages. The results are promising that RuleLLM generated 763 rules (452 YARA and 311 Semgrep) with a precision of 85.2\% and a recall of 91.8\%, outperforming state-of-the-art (SOTA) tools and scored-based approaches. We further analyzed generated rules and proposed a rule taxonomy: 11 categories and 38 subcategories.
Open AccessAutomatically Generating Rules of Malicious Software Packages via Large Language Model
Today's security tools predominantly rely on predefined rules crafted by experts, making them poorly adapted to the emergence of software supply chain attacks. To tackle this limitation, we propose a novel tool, RuleLLM, which leverages large language models (LLMs) to automate rule generation for OSS ecosystems. RuleLLM extracts metadata and code snippets from malware as its input, producing YARA and Semgrep rules that can be directly deployed in software development. Specifically, the rule generation task involves three subtasks: crafting rules, refining rules, and aligning rules. To validate RuleLLM's effectiveness, we implemented a prototype system and conducted experiments on the dataset of 1,633 malicious packages. The results are promising that RuleLLM generated 763 rules (452 YARA and 311 Semgrep) with a precision of 85.2\% and a recall of 91.8\%, outperforming state-of-the-art (SOTA) tools and scored-based approaches. We further analyzed generated rules and proposed a rule taxonomy: 11 categories and 38 subcategories.
- 18 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 4484-4497
SoFi: Spoofing OS Fingerprints Against Network Reconnaissance
Fingerprinting is a network reconnaissance technique utilized for gathering information about online computing systems, including operation systems and applications. Unfortunately, attackers typically leverage fingerprinting techniques to locate, enumerate, and subsequently target vulnerable systems, which is the first primary stage of a cyber attack. In this work, we explore the susceptibility of machine learning (ML)-based classifiers to misclassification, where a slight perturbation in the packet is included to spoof OS fingerprints. We propose SOFI (Spoof OS Fingerprints), an adversarial example generation algorithm under TCP/IP specification constraints, to create effective perturbations in a packet for deceiving an OS fingerprint. Specifically, SOFI has three major technical innovations: (1) it is the first to utilize adversarial examples to automatically perturb fingerprinting techniques; (2) it complies with constraints and integrity of network packets; (3) it achieves a high success rate in spoofing OS fingerprints. We validate the effectiveness of adversarial packets against active and passive OS fingerprints, verifying the transferability and robustness of SOFI. Comprehensive experimental results demonstrate that SOFI automatically identifies applicable and available OS fingerprint features, unlike existing tools relying on expert knowledge.
- 18 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 4484-4497
SoFi: Spoofing OS Fingerprints Against Network Reconnaissance
Fingerprinting is a network reconnaissance technique utilized for gathering information about online computing systems, including operation systems and applications. Unfortunately, attackers typically leverage fingerprinting techniques to locate, enumerate, and subsequently target vulnerable systems, which is the first primary stage of a cyber attack. In this work, we explore the susceptibility of machine learning (ML)-based classifiers to misclassification, where a slight perturbation in the packet is included to spoof OS fingerprints. We propose SOFI (Spoof OS Fingerprints), an adversarial example generation algorithm under TCP/IP specification constraints, to create effective perturbations in a packet for deceiving an OS fingerprint. Specifically, SOFI has three major technical innovations: (1) it is the first to utilize adversarial examples to automatically perturb fingerprinting techniques; (2) it complies with constraints and integrity of network packets; (3) it achieves a high success rate in spoofing OS fingerprints. We validate the effectiveness of adversarial packets against active and passive OS fingerprints, verifying the transferability and robustness of SOFI. Comprehensive experimental results demonstrate that SOFI automatically identifies applicable and available OS fingerprint features, unlike existing tools relying on expert knowledge.
- 25 December 2024
- Published by Springer Nature
- p. 310-331
FirmPorter: Porting RTOSes at the Binary Level for Firmware Re-hosting
- 25 December 2024
- Published by Springer Nature
- p. 310-331
FirmPorter: Porting RTOSes at the Binary Level for Firmware Re-hosting
- 13 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (6) , 7195-7208
Detecting Time-Delay Attacks in Industrial Control Systems Through State-Aware Inference
The time-delay attacks pose serious security threats to the industrial control systems (ICSs), where ICS infrastructures (e.g., chemical factories) could suffer severe safety consequences. They could bypass current delay detection methods by avoiding triggering packet timeouts. In this article, we reveal that malicious states caused by the time-delay attacks in ICS scenarios can be detected by analyzing ICS programs. We propose detecting a time-delay attack in ICS scenarios by comparing the difference between malicious and benign states, meeting the real-time and noninterference requirements. Specifically, we utilize symbolic execution to analyze ICS programs to generate the benign states of ICS and leverage the key features of time-delay attacks to create the malicious states of ICS, where the states are transferred through the network for remote control and monitoring. We propose a multimodal neural network whose inputs are the malicious states sampled from the ICS network traffic and the time domain features, and the output is whether such a time-delay attack exists. We implement a prototype system and conduct real-world experiments to evaluate the performance of our detection approach. Our experiments cover 102 vulnerable ICS programs and five types of time-delay attacks. The evaluation results show that our approach can detect ICS time-delay attacks in 0.6 s, with 97.2% precision and 98% recall.
- 13 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (6) , 7195-7208
Detecting Time-Delay Attacks in Industrial Control Systems Through State-Aware Inference
The time-delay attacks pose serious security threats to the industrial control systems (ICSs), where ICS infrastructures (e.g., chemical factories) could suffer severe safety consequences. They could bypass current delay detection methods by avoiding triggering packet timeouts. In this article, we reveal that malicious states caused by the time-delay attacks in ICS scenarios can be detected by analyzing ICS programs. We propose detecting a time-delay attack in ICS scenarios by comparing the difference between malicious and benign states, meeting the real-time and noninterference requirements. Specifically, we utilize symbolic execution to analyze ICS programs to generate the benign states of ICS and leverage the key features of time-delay attacks to create the malicious states of ICS, where the states are transferred through the network for remote control and monitoring. We propose a multimodal neural network whose inputs are the malicious states sampled from the ICS network traffic and the time domain features, and the output is whether such a time-delay attack exists. We implement a prototype system and conduct real-world experiments to evaluate the performance of our detection approach. Our experiments cover 102 vulnerable ICS programs and five types of time-delay attacks. The evaluation results show that our approach can detect ICS time-delay attacks in 0.6 s, with 97.2% precision and 98% recall.
- Open Access
A Large-scale Fine-grained Analysis of Packages in Open-Source Software Ecosystems
Package managers such as NPM, Maven, and PyPI play a pivotal role in open-source software (OSS) ecosystems, streamlining the distribution and management of various freely available packages. The fine-grained details within software packages can unveil potential risks within existing OSS ecosystems, offering valuable insights for detecting malicious packages. In this study, we undertake a large-scale empirical analysis focusing on fine-grained information (FGI): the metadata, static, and dynamic functions. Specifically, we investigate the FGI usage across a diverse set of 50,000+ legitimate and 1,000+ malicious packages. Based on this diverse data collection, we conducted a comparative analysis between legitimate and malicious packages. Our findings reveal that (1) malicious packages have less metadata content and utilize fewer static and dynamic functions than legitimate ones; (2) malicious packages demonstrate a higher tendency to invoke HTTP/URL functions as opposed to other application services, such as FTP or SMTP; (3) FGI serves as a distinguishable indicator between legitimate and malicious packages; and (4) one dimension in FGI has sufficient distinguishable capability to detect malicious packages, and combining all dimensions in FGI cannot significantly improve overall performance.
Open AccessA Large-scale Fine-grained Analysis of Packages in Open-Source Software Ecosystems
Package managers such as NPM, Maven, and PyPI play a pivotal role in open-source software (OSS) ecosystems, streamlining the distribution and management of various freely available packages. The fine-grained details within software packages can unveil potential risks within existing OSS ecosystems, offering valuable insights for detecting malicious packages. In this study, we undertake a large-scale empirical analysis focusing on fine-grained information (FGI): the metadata, static, and dynamic functions. Specifically, we investigate the FGI usage across a diverse set of 50,000+ legitimate and 1,000+ malicious packages. Based on this diverse data collection, we conducted a comparative analysis between legitimate and malicious packages. Our findings reveal that (1) malicious packages have less metadata content and utilize fewer static and dynamic functions than legitimate ones; (2) malicious packages demonstrate a higher tendency to invoke HTTP/URL functions as opposed to other application services, such as FTP or SMTP; (3) FGI serves as a distinguishable indicator between legitimate and malicious packages; and (4) one dimension in FGI has sufficient distinguishable capability to detect malicious packages, and combining all dimensions in FGI cannot significantly improve overall performance.
- 9 December 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 284
Understanding images of surveillance devices in the wild
- 9 December 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 284
Understanding images of surveillance devices in the wild
- 28 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 21 (4) , 3785-3800
PKVIC: Supplement Missing Software Package Information in Security Vulnerability Reports
Nowadays security vulnerability reports contain commercial vendor-centric information but fail to include accurate information of open-source software packages. Open-source ecosystems use package managers, such as Maven, NuGet, NPM, and Gem, to cover hundreds of thousands of free code packages. However, we uncover that vulnerability reports frequently miss the vulnerable software package information when the software package comes from open-source ecosystems. To fill in this gap, we propose a framework called PKVIC (software p ac k age v ulnerability i nformation c alibration), as the first tool to automatically associate security vulnerability reports with affected software packages from different open-source ecosystems. Specifically, PKVIC designs an ecosystem classifier to determine which ecosystem a vulnerability report belongs to. From the reports written in natural language, PKVIC extracts the entities closely related to software names in ecosystems. To efficiently and accurately locate the affected software packages from millions of packages, we propose a recursive traversal method to generate the package identifier based on the naming scheme and candidate named entities. We implemented the prototype of PKVIC and conducted comprehensive experiments to validate its efficacy. In particular, we ran PKVIC over 421,808 vulnerability reports from 20 well-known sources of security vulnerabilities and identified 11,279 unique vulnerability reports that affected 2,703 open-source software packages. PKVIC successfully found the accurate reference URLs for these 2,703 software packages across 6 open-source ecosystems, including Pypi, Gem, NPM, Packagist, Nuget, and Maven.
- 28 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 21 (4) , 3785-3800
PKVIC: Supplement Missing Software Package Information in Security Vulnerability Reports
Nowadays security vulnerability reports contain commercial vendor-centric information but fail to include accurate information of open-source software packages. Open-source ecosystems use package managers, such as Maven, NuGet, NPM, and Gem, to cover hundreds of thousands of free code packages. However, we uncover that vulnerability reports frequently miss the vulnerable software package information when the software package comes from open-source ecosystems. To fill in this gap, we propose a framework called PKVIC (software p ac k age v ulnerability i nformation c alibration), as the first tool to automatically associate security vulnerability reports with affected software packages from different open-source ecosystems. Specifically, PKVIC designs an ecosystem classifier to determine which ecosystem a vulnerability report belongs to. From the reports written in natural language, PKVIC extracts the entities closely related to software names in ecosystems. To efficiently and accurately locate the affected software packages from millions of packages, we propose a recursive traversal method to generate the package identifier based on the naming scheme and candidate named entities. We implemented the prototype of PKVIC and conducted comprehensive experiments to validate its efficacy. In particular, we ran PKVIC over 421,808 vulnerability reports from 20 well-known sources of security vulnerabilities and identified 11,279 unique vulnerability reports that affected 2,703 open-source software packages. PKVIC successfully found the accurate reference URLs for these 2,703 software packages across 6 open-source ecosystems, including Pypi, Gem, NPM, Packagist, Nuget, and Maven.
- Open Access
- 19 October 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 20 (1) , 1-26
Toward Automatically Connecting IoT Devices with Vulnerabilities in the Wild
With the increasing number of Internet of Things (IoT) devices connected to the internet, the industry and research community have become increasingly concerned about their security impact. Adversaries or hackers often exploit public security flaws to compromise IoT devices and launch cyber attacks. However, despite this growing concern, little effort has been made to investigate the detection of IoT devices and their underlying risks. To address this gap, this article proposes to automatically establish relationships between IoT devices and their vulnerabilities in the wild. Specifically, we construct a deep neural network (DNN) to extract semantic information from IoT packets and generate fine-grained fingerprints of IoT devices. This enables us to annotate IoT devices in cyberspace, including their device type, vendor, and product information. We collect vulnerability reports from various security sources and extract IoT device information from these reports to automatically match vulnerabilities with the fingerprints of IoT devices. We implemented a prototype system and conducted extensive experiments to validate the effectiveness of our approach. The results show that our DNN model achieved a 98% precision rate and a 95% recall rate in IoT device fingerprinting. Furthermore, we collected and analyzed over 13,063 IoT-related vulnerability reports and our method automatically built 5,458 connections between IoT device fingerprints and their vulnerabilities. These findings shed light on the ongoing threat of cyber-attacks on IoT systems as both IoT devices and disclosed vulnerabilities are targets for malicious attackers.
- 19 October 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 20 (1) , 1-26
Open AccessToward Automatically Connecting IoT Devices with Vulnerabilities in the Wild
With the increasing number of Internet of Things (IoT) devices connected to the internet, the industry and research community have become increasingly concerned about their security impact. Adversaries or hackers often exploit public security flaws to compromise IoT devices and launch cyber attacks. However, despite this growing concern, little effort has been made to investigate the detection of IoT devices and their underlying risks. To address this gap, this article proposes to automatically establish relationships between IoT devices and their vulnerabilities in the wild. Specifically, we construct a deep neural network (DNN) to extract semantic information from IoT packets and generate fine-grained fingerprints of IoT devices. This enables us to annotate IoT devices in cyberspace, including their device type, vendor, and product information. We collect vulnerability reports from various security sources and extract IoT device information from these reports to automatically match vulnerabilities with the fingerprints of IoT devices. We implemented a prototype system and conducted extensive experiments to validate the effectiveness of our approach. The results show that our DNN model achieved a 98% precision rate and a 95% recall rate in IoT device fingerprinting. Furthermore, we collected and analyzed over 13,063 IoT-related vulnerability reports and our method automatically built 5,458 connections between IoT device fingerprints and their vulnerabilities. These findings shed light on the ongoing threat of cyber-attacks on IoT systems as both IoT devices and disclosed vulnerabilities are targets for malicious attackers.
- 1 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 384-389
Generalized Zero-Shot Learning via Implicit Attribute Composition
Zero-shot learning (ZSL) is an important but challenging task in computer vision that aims to identify unseen classes without matching training samples. Current cutting-edge ZSL methods based on locality focus on acquiring the explicit locality of distinguishing characteristics, which could face a lack of adequate supervision at the class attribute level. This paper introduces a novel approach called IAC, which aims to learn Implicit Attribute Composition for ZSL. This method is more comprehensive compared to attribute localization that solely focuses on class-level attribute supervision. IAC utilizes subspace representations that efficiently capture the inherent structure of high-dimensional image features. Then, we learn implicit attribute composition through subspace representation learning. The superiority of the proposed IAC compared to the state-of-the-art is demonstrated through sufficient experiments conducted on three commonly used ZSL datasets, CUB, SUN, and AwA2.
- 1 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 384-389
Generalized Zero-Shot Learning via Implicit Attribute Composition
Zero-shot learning (ZSL) is an important but challenging task in computer vision that aims to identify unseen classes without matching training samples. Current cutting-edge ZSL methods based on locality focus on acquiring the explicit locality of distinguishing characteristics, which could face a lack of adequate supervision at the class attribute level. This paper introduces a novel approach called IAC, which aims to learn Implicit Attribute Composition for ZSL. This method is more comprehensive compared to attribute localization that solely focuses on class-level attribute supervision. IAC utilizes subspace representations that efficiently capture the inherent structure of high-dimensional image features. Then, we learn implicit attribute composition through subspace representation learning. The superiority of the proposed IAC compared to the state-of-the-art is demonstrated through sufficient experiments conducted on three commonly used ZSL datasets, CUB, SUN, and AwA2.
- 5 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 21 (2) , 905-919
Automatically Identifying CVE Affected Versions With Patches and Developer Logs
While vulnerability databases are important sources of information for software security, it is known that information in these databases is inconsistent. How to rectify these incorrect data is a challenging issue. In this paper, we employ developer logs and patches to automatically identify vulnerable source code versions that each CVE really affects. Our tool organizes all versions of a piece of software into a version tree, and identifies the first vulnerable version, and the last vulnerable versions in the version tree trunk and branches. For evaluation, we took Linux Kernel as the case study and quantified the error rate of the vulnerable versions reported by the NVD. The total number of vulnerable Linux Kernel versions reported by the NVD was 43,727 (as of September 2020), of which the total number of false positives reached 2,497 and the total number of false negatives reached 9,330, accounting for 5.7% and 21.34%, respectively. In addition, we compare our tool with two vulnerability detection tools and show that our tool could achieve high detection accuracy.
- 5 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 21 (2) , 905-919
Automatically Identifying CVE Affected Versions With Patches and Developer Logs
While vulnerability databases are important sources of information for software security, it is known that information in these databases is inconsistent. How to rectify these incorrect data is a challenging issue. In this paper, we employ developer logs and patches to automatically identify vulnerable source code versions that each CVE really affects. Our tool organizes all versions of a piece of software into a version tree, and identifies the first vulnerable version, and the last vulnerable versions in the version tree trunk and branches. For evaluation, we took Linux Kernel as the case study and quantified the error rate of the vulnerable versions reported by the NVD. The total number of vulnerable Linux Kernel versions reported by the NVD was 43,727 (as of September 2020), of which the total number of false positives reached 2,497 and the total number of false negatives reached 9,330, accounting for 5.7% and 21.34%, respectively. In addition, we compare our tool with two vulnerability detection tools and show that our tool could achieve high detection accuracy.