Xiangkun Jia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiangkun Jia has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Purui Su
Institute of Software, Chinese Academy of Sciences, Beijing, Beijing, China
3 shared publications - Yanhao Wang
Shanghai Jiao Tong University
2 shared publications - Yuwei Liu
Institute of Software at Chinese Academy of Sciences, Beijing, China
2 shared publications Chao Zhang
Institute for Network Science and Cyberspace of Tsinghua University, China and Zhongguancun Lab, China
1 shared publication- Jia Yan
TCA/SKLCS, Institute of Software, Chinese Academy of Sciences, China and School of Computer Science and Technology, University of Chinese Academy of Sciences, China
1 shared publication - Junquan Deng
Institute of Software Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1559-1573
P rome F uzz : A Knowledge-Driven Approach to Fuzzing Harness Generation with Large Language Models
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1559-1573
Open AccessP rome F uzz : A Knowledge-Driven Approach to Fuzzing Harness Generation with Large Language Models
- Open Access
- 5 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 227-239
DitDetector: Bimodal Learning based on Deceptive Image and Text for Macro Malware Detection
Macro malware has always been a severe threat to cyber security although the Microsoft Office suite applies the default macro-disabling policy. Among the defense solutions at different stages of the attack chain, document analysis is more targeted through detecting malicious documents with macro malware. It is effective, especially with machine learning methods, but still faces problems handling malware variants, supporting file formats, and attack countermeasures with advanced attack techniques (e.g., Excel 4.0 macro and remote template injection). In this paper, we find it promising to detect deceptive information embedded in documents which tricks users into enabling macros instead of detecting file metadata or extracted macro codes. Thus, we propose a novel solution for macro malware detection named DitDetector, which leverages bimodal learning based on deceptive images and text. Specifically, we extract preview images of documents based on an image export SDK of Oracle and extract textual information from preview images based on an open-source OCR engine. The bimodal model of DitDetector contains a visual encoder, a textual encoder, and a forward neural network, which learns based on the joint representation of the two encoders’ outputs. We evaluate DitDetector on three datasets, including an open-source malicious document dataset (i.e., MalDoc) and two collected real-world adversary datasets (i.e., a database of Excel macros and a database of remote template injection samples). Our experiments show that DitDetector outperforms four existing macro code-based machine learning methods and five reputable Anti-Virus engines. Especially in the real-world test of advanced macro malware, DitDetector gets the F1-score of 99.93% which is at least 3.16% higher than compared solutions.
- 5 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 227-239
Open AccessDitDetector: Bimodal Learning based on Deceptive Image and Text for Macro Malware Detection
Macro malware has always been a severe threat to cyber security although the Microsoft Office suite applies the default macro-disabling policy. Among the defense solutions at different stages of the attack chain, document analysis is more targeted through detecting malicious documents with macro malware. It is effective, especially with machine learning methods, but still faces problems handling malware variants, supporting file formats, and attack countermeasures with advanced attack techniques (e.g., Excel 4.0 macro and remote template injection). In this paper, we find it promising to detect deceptive information embedded in documents which tricks users into enabling macros instead of detecting file metadata or extracted macro codes. Thus, we propose a novel solution for macro malware detection named DitDetector, which leverages bimodal learning based on deceptive images and text. Specifically, we extract preview images of documents based on an image export SDK of Oracle and extract textual information from preview images based on an open-source OCR engine. The bimodal model of DitDetector contains a visual encoder, a textual encoder, and a forward neural network, which learns based on the joint representation of the two encoders’ outputs. We evaluate DitDetector on three datasets, including an open-source malicious document dataset (i.e., MalDoc) and two collected real-world adversary datasets (i.e., a database of Excel macros and a database of remote template injection samples). Our experiments show that DitDetector outperforms four existing macro code-based machine learning methods and five reputable Anti-Virus engines. Especially in the real-world test of advanced macro malware, DitDetector gets the F1-score of 99.93% which is at least 3.16% higher than compared solutions.
- Open Access
- 10 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-13
HTFuzz: Heap Operation Sequence Sensitive Fuzzing
Heap-based temporal vulnerabilities (i.e., use-after-free, double-free and null pointer dereference) are highly sensitive to heap operation (e.g., memory allocation, deallocation and access) sequences. To efficiently find such vulnerabilities, traditional code coverage-guided fuzzing solutions could be promoted by integrating heap operation sequence feedback. But current sequence sensitive solutions have limitations in practice. In this paper, we propose a novel fuzzing solution named HTFuzz, to find heap-based temporal vulnerabilities. At the core, we utilize fuzzing to increase the coverage of runtime heap operation sequences and the diversity of pointers accessed by these operations, where the former reflects the control-flow and the latter reflects the data-flow of heap operation sequences. With such increases, the fuzzer could find more heap-based temporal vulnerabilities. We have developed a prototype of HTFuzz and evaluated it on 14 real-world applications, and compared it with 11 state-of-the-art fuzzers. The results showed that, HTFuzz outperformed all the baselines and was statistically better on the number of heap-based temporal vulnerabilities discovered. In detail, HTFuzz found (1.82x, 2.62x, 2.66x, 2.02x, 2.21x, 2.06x, 1.47x, 2.98x, 1.98x) more heap operation sequences and (1.45x, 3.56x, 3.56x, 4.57x, 1.78x, 1.78x, 1.68x, 4.00x, 1.45x) more 0day heap-based temporal vulnerabilities than (AFL, AFL-sensitive-ma, AFL-sensitive-mw, Memlock, PathAFL, TortoiseFuzz, MOPT, Angora, Ankou), respectively. HTFuzz discovered 37 new vulnerabilities with 37 CVEs assigned, including 32 new heap-based temporal vulnerabilities and 5 of other types.
- 10 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Open AccessHTFuzz: Heap Operation Sequence Sensitive Fuzzing
Heap-based temporal vulnerabilities (i.e., use-after-free, double-free and null pointer dereference) are highly sensitive to heap operation (e.g., memory allocation, deallocation and access) sequences. To efficiently find such vulnerabilities, traditional code coverage-guided fuzzing solutions could be promoted by integrating heap operation sequence feedback. But current sequence sensitive solutions have limitations in practice. In this paper, we propose a novel fuzzing solution named HTFuzz, to find heap-based temporal vulnerabilities. At the core, we utilize fuzzing to increase the coverage of runtime heap operation sequences and the diversity of pointers accessed by these operations, where the former reflects the control-flow and the latter reflects the data-flow of heap operation sequences. With such increases, the fuzzer could find more heap-based temporal vulnerabilities. We have developed a prototype of HTFuzz and evaluated it on 14 real-world applications, and compared it with 11 state-of-the-art fuzzers. The results showed that, HTFuzz outperformed all the baselines and was statistically better on the number of heap-based temporal vulnerabilities discovered. In detail, HTFuzz found (1.82x, 2.62x, 2.66x, 2.02x, 2.21x, 2.06x, 1.47x, 2.98x, 1.98x) more heap operation sequences and (1.45x, 3.56x, 3.56x, 4.57x, 1.78x, 1.78x, 1.68x, 4.00x, 1.45x) more 0day heap-based temporal vulnerabilities than (AFL, AFL-sensitive-ma, AFL-sensitive-mw, Memlock, PathAFL, TortoiseFuzz, MOPT, Angora, Ankou), respectively. HTFuzz discovered 37 new vulnerabilities with 37 CVEs assigned, including 32 new heap-based temporal vulnerabilities and 5 of other types.