Gelei Deng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Gelei Deng has a total of 71 co-authors. Here are the top co-authors by number of shared publications:
- Yi Liu
Griffith University, Gold Coast, Australia
10 shared publications - Tianwei Zhang
Nanyang technological university, Singapore, Singapore
9 shared publications - Yuekang Li
University of New South Wales, Sydney, NSW, Australia
7 shared publications - Kailong Wang
National University of Singapore
5 shared publications - Yang Liu
Department of Obstetrics and Gynecology, The Second Affiliated Hospital of Kunming Medical University, China
5 shared publications - Han Qiu
Tsinghua University, Beijing, China
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7922-7931
Beyond Retrieval: Improving Evidence Quality for LLM-based Multimodal Fact-Checking
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7922-7931
Open AccessBeyond Retrieval: Improving Evidence Quality for LLM-based Multimodal Fact-Checking
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 3373-3376
SAF: An AI-Agent-Ready and Browser-Accessible Static Analysis Framework for LLVM IR
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 3373-3376
Open AccessSAF: An AI-Agent-Ready and Browser-Accessible Static Analysis Framework for LLVM IR
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 536-548
How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study
Large Language Model (LLM) agents increasingly rely on third-party skills that operate within privileged execution environments and routinely handle sensitive credentials, yet how these credentials are leaked remains largely unexplored. To fill this gap, we present the first large-scale empirical study on credential leakage in agent skills. From 170,226 artifacts on SkillsMP, the largest open-source skill marketplace, we sampled 17,022 skills via stratified random sampling and analyzed each through static secret extraction (regex and AST parsing), dynamic sandbox testing of flagged candidates seeded with mock credentials, and cross-referencing developer intent against runtime behavior. Our analysis identifies 520 affected skills containing 1,708 security issues, and yields a taxonomy of 10 leakage patterns. Three findings stand out. First, 76.3% of cases require jointly analyzing natural-language descriptions and programming logic, showing that credential exposure in skills is fundamentally cross-modal. Second, Information Exposure accounts for 73.5% of vulnerability issues because agent frameworks feed stdout into the LLM context window, turning routine debugging into a credential exposure vector. Third, 89.6% of leaked credentials are immediately exploitable, and the fork-based distribution model defeats remediation, as secrets removed from upstream repositories persist across 50+ independent forks. Following responsible disclosure, all malicious skills have been removed. We release our dataset, taxonomy, and detection pipeline to support future agent security research.
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 536-548
Open AccessHow Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study
Large Language Model (LLM) agents increasingly rely on third-party skills that operate within privileged execution environments and routinely handle sensitive credentials, yet how these credentials are leaked remains largely unexplored. To fill this gap, we present the first large-scale empirical study on credential leakage in agent skills. From 170,226 artifacts on SkillsMP, the largest open-source skill marketplace, we sampled 17,022 skills via stratified random sampling and analyzed each through static secret extraction (regex and AST parsing), dynamic sandbox testing of flagged candidates seeded with mock credentials, and cross-referencing developer intent against runtime behavior. Our analysis identifies 520 affected skills containing 1,708 security issues, and yields a taxonomy of 10 leakage patterns. Three findings stand out. First, 76.3% of cases require jointly analyzing natural-language descriptions and programming logic, showing that credential exposure in skills is fundamentally cross-modal. Second, Information Exposure accounts for 73.5% of vulnerability issues because agent frameworks feed stdout into the LLM context window, turning routine debugging into a credential exposure vector. Third, 89.6% of leaked credentials are immediately exploitable, and the fork-based distribution model defeats remediation, as secrets removed from upstream repositories persist across 50+ independent forks. Following responsible disclosure, all malicious skills have been removed. We release our dataset, taxonomy, and detection pipeline to support future agent security research.
- 4 August 2026
- Published by Springer Nature
- p. 61-76
Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
- 4 August 2026
- Published by Springer Nature
- p. 61-76
Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
- Open Access
- 24 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (5) , 1-25
SPOLRE: Semantic Preserving Object Layout Reconstruction for Image Captioning System Testing
Image captioning (IC) systems, including Microsoft Azure Cognitive Service, are commonly utilized to convert image content into descriptive natural language. However, inaccuracies in caption generation can lead to serious misinterpretations. Advanced testing techniques such as MetaIC and ROME have been developed to mitigate these issues, yet they encounter notable challenges. First, these strategies demand intensive labor, relying on detailed manual annotations like bounding box data of objects to create test cases. Second, the realism of the generated images is compromised, with MetaIC adding unrelated objects and ROME failing to remove objects effectively. Finally, the capability to generate diversified test suites is restricted. MetaIC is limited to only inserting specific objects to prevent overlap, whereas ROME can generate only \(3^{n}-2^{n}\) variations of test cases from an original seed image containing \( n \) objects. In this study, we present SPOLRE, a novel automated tool designed for semantic preserving object layout reconstruction in image captioning system testing. SPOLRE is based on the insight that modifying the arrangement of objects within an image does not alter its inherent semantics. We utilize four semantic preserving transformation techniques—translation, rotation, mirroring, and scaling—to modify object layouts autonomously, eliminating the need for manual annotation. This approach enables the creation of realistic and varied test suites for IC system testing. Our extensive testing demonstrates that more than 75% of survey respondents find the images produced by SPOLRE more realistic compared to those generated by SOTA methods. Additionally, SPOLRE exhibits outstanding performance in identifying caption errors, detecting 31,544 incorrect captions across seven IC systems with an average precision of 91.62%. This significantly outperforms other methods, which only achieve 85.65% accuracy on average and identify 17,160 incorrect captions. Notably, SPOLRE exposes 6,236 unique issues within Microsoft Azure Cognitive Service, highlighting its effectiveness against one of the most advanced IC systems available.- 24 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (5) , 1-25
Open AccessSPOLRE: Semantic Preserving Object Layout Reconstruction for Image Captioning System Testing
Image captioning (IC) systems, including Microsoft Azure Cognitive Service, are commonly utilized to convert image content into descriptive natural language. However, inaccuracies in caption generation can lead to serious misinterpretations. Advanced testing techniques such as MetaIC and ROME have been developed to mitigate these issues, yet they encounter notable challenges. First, these strategies demand intensive labor, relying on detailed manual annotations like bounding box data of objects to create test cases. Second, the realism of the generated images is compromised, with MetaIC adding unrelated objects and ROME failing to remove objects effectively. Finally, the capability to generate diversified test suites is restricted. MetaIC is limited to only inserting specific objects to prevent overlap, whereas ROME can generate only \(3^{n}-2^{n}\) variations of test cases from an original seed image containing \( n \) objects. In this study, we present SPOLRE, a novel automated tool designed for semantic preserving object layout reconstruction in image captioning system testing. SPOLRE is based on the insight that modifying the arrangement of objects within an image does not alter its inherent semantics. We utilize four semantic preserving transformation techniques—translation, rotation, mirroring, and scaling—to modify object layouts autonomously, eliminating the need for manual annotation. This approach enables the creation of realistic and varied test suites for IC system testing. Our extensive testing demonstrates that more than 75% of survey respondents find the images produced by SPOLRE more realistic compared to those generated by SOTA methods. Additionally, SPOLRE exhibits outstanding performance in identifying caption errors, detecting 31,544 incorrect captions across seven IC systems with an average precision of 91.62%. This significantly outperforms other methods, which only achieve 85.65% accuracy on average and identify 17,160 incorrect captions. Notably, SPOLRE exposes 6,236 unique issues within Microsoft Azure Cognitive Service, highlighting its effectiveness against one of the most advanced IC systems available. - Open Access
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6-20
Oedipus: LLM-enchanced Reasoning CAPTCHA Solver
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6-20
Open AccessOedipus: LLM-enchanced Reasoning CAPTCHA Solver
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 3683-3691
IllusionCAPTCHA: A CAPTCHA based on Visual Illusion
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 3683-3691
Open AccessIllusionCAPTCHA: A CAPTCHA based on Visual Illusion
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1879-1893
PhyScout: Detecting Sensor Spoofing Attacks via Spatio-temporal Consistency
Existing defense approaches against sensor spoofing attacks suffer from the limitations of limited specific attack types, requiring GPU computation, exhibiting considerable detection latency and struggling with the interpretability of corner cases. We developed PhyScout, a holistic sensor spoofing defense framework to overcome the above limitations. Our framework capitalizes on the observation that human drivers can rapidly and accurately identify spoofing attacks by performing spatio-temporal consistency checks of their environment. We commence by defining the generalized conflicts that different sensor spoofing attacks produce regarding the spatio-temporal consistency. These conflicts are subsequently unified and formalized through a least squares problem approach. This process is modeled using image-based feature point extraction and matching techniques, followed by the design of a risk identification method for each conflict. We evaluate PhyScout across various environments, including simulators, datasets, and real-world scenarios. Compared to existing defense solutions, PhyScout offers rapid identification of sensor attacks (within 100ms) with low performance overhead (CPU-based), and conflict visualization. It demonstrates a fresh paradigm in autonomous vehicle security and presents new avenues for future research in robust and efficient defense mechanisms against sensor spoofing attacks. More video demos are at our anonymous website https://sites.google.com/view/physcout.
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1879-1893
Open AccessPhyScout: Detecting Sensor Spoofing Attacks via Spatio-temporal Consistency
Existing defense approaches against sensor spoofing attacks suffer from the limitations of limited specific attack types, requiring GPU computation, exhibiting considerable detection latency and struggling with the interpretability of corner cases. We developed PhyScout, a holistic sensor spoofing defense framework to overcome the above limitations. Our framework capitalizes on the observation that human drivers can rapidly and accurately identify spoofing attacks by performing spatio-temporal consistency checks of their environment. We commence by defining the generalized conflicts that different sensor spoofing attacks produce regarding the spatio-temporal consistency. These conflicts are subsequently unified and formalized through a least squares problem approach. This process is modeled using image-based feature point extraction and matching techniques, followed by the design of a risk identification method for each conflict. We evaluate PhyScout across various environments, including simulators, datasets, and real-world scenarios. Compared to existing defense solutions, PhyScout offers rapid identification of sensor attacks (within 100ms) with low performance overhead (CPU-based), and conflict visualization. It demonstrates a fresh paradigm in autonomous vehicle security and presents new avenues for future research in robust and efficient defense mechanisms against sensor spoofing attacks. More video demos are at our anonymous website https://sites.google.com/view/physcout.