Dr. Lingxin Jin, University of Electronic Science and Technology of China
Dr. Lingxin Jin, based in Chengdu, China, is a Ph.D. candidate in Software Engineering at the University of Electronic Science and Technology of China, where he also completed his Bachelor’s degree with a GPA of 3.8/4.0. His academic focus includes artificial intelligence, machine learning, network security, and software systems. Dr. Jin has gained international experience through an exchange program at the International Technological University in Silicon Valley and held internships involving front-end development and research on backdoor attacks against deep neural networks. His research contributions include publications in high-impact journals such as IEEE Transactions on Computers and the Journal of Circuits, Systems, and Computers, with additional submissions to ACM and IJCAI. Dr. Jin has worked on projects ranging from Linux shell simulations to public opinion analysis systems. He has received several scholarships and honors, including direct Ph.D. program recommendation, and is recognized for his promising research in AI security and adversarial attacks.
Publication Profile
Scopus
Orcid
🎓 Educational Background
Dr. Lingxin Jin pursued his academic journey in Software Engineering at the University of Electronic Science and Technology of China. He completed his Bachelor’s degree from September 2018 to June 2022, achieving an impressive GPA of 3.8/4.0. During his undergraduate studies, he built a strong foundation through comprehensive coursework in Software Engineering, Computer Networks, Operating Systems, and Artificial Intelligence. Driven by academic excellence, Dr. Jin was recommended for direct entry into the Ph.D. program, which he began in September 2022. Currently, he is a Ph.D. candidate in Software Engineering at the same university, maintaining a GPA of 3.71/4.0. His advanced studies focus on cutting-edge topics such as Information Security Fundamentals and Frontiers, Network Security Theory and Technology, Machine Learning Theory and Algorithms, and Statistical Machine Learning. This academic background highlights his commitment to research and innovation in secure intelligent systems and computational technologies.
💼 Professional Experience
Dr. Lingxin Jin has gained diverse and valuable professional experience that complements his academic pursuits in software engineering and artificial intelligence. In July 2019, he participated in an exchange program at the International Technological University in Silicon Valley, where he engaged in programming robot motion manipulation using Raspberry Pi and Arduino, as well as composing songs using MATLAB—demonstrating his multidisciplinary creativity. From January to June 2021, Dr. Jin interned at Xi’an Deta Information Technology Co., where he focused on front-end development and contributed to building an opinion analysis system. This role honed his skills in UI/UX and real-time data interpretation. He later served as a Software Engineer Intern at Sichuan Meiliankai Science and Technology Co. from September 2021 to June 2022, where he conducted advanced research on backdoor attacks against deep neural networks. These experiences collectively reflect Dr. Jin’s technical versatility and growing expertise in cybersecurity and intelligent systems.
🏅 Additional Experience and Awards
Dr. Lingxin Jin has consistently demonstrated academic excellence throughout his educational journey, earning multiple awards and recognitions. During his undergraduate studies from 2018 to 2022 at the University of Electronic Science and Technology of China, he was honored with first and second-class scholarships for outstanding academic performance. His dedication and scholarly achievements earned him a prestigious recommendation for direct admission into the Ph.D. program, a distinction reserved for top-performing students. As a postgraduate student from 2022 onward, Dr. Jin continued to excel, receiving scholarships for new students as well as second-class scholarships for academic distinction. These accolades not only highlight his strong academic capabilities but also reflect his commitment to advancing in the field of software engineering and artificial intelligence. Dr. Jin’s consistent recognition at both undergraduate and postgraduate levels underscores his potential as a future leader in cutting-edge technological research and innovation.
🧠 Research Focus
Dr. Lingxin Jin’s research primarily focuses on adversarial machine learning, with a particular emphasis on Trojan attacks and security vulnerabilities in deep neural networks (DNNs). His scholarly work explores the life-cycle threats faced by DNNs, covering both attack strategies and defensive countermeasures. His publication in ACM Computing Surveys titled “Trojan Attacks and Countermeasures on Deep Neural Networks from Life-Cycle Perspective” provides a comprehensive overview of attack surfaces throughout a model’s development and deployment phases. Additionally, his work in IEEE Transactions on Computers, “Highly Evasive Targeted Bit-Trojan on Deep Neural Networks”, introduces novel methods of crafting stealthy, highly targeted Trojans that evade standard detection techniques. Through these contributions, Dr. Jin is advancing the field of AI security, focusing on the resilience and trustworthiness of neural networks in critical applications. His research is vital for developing robust defense frameworks and ensuring safe deployment of AI systems in real-world scenarios.
Publication Top Notes
-
📄 2024: “Highly Evasive Targeted Bit‑Trojan on Deep Neural Networks” (IEEE Trans. on Computers) – DOI:10.1109/TC.2024.3416705; introduces stealthy bit-level Trojans; cited 2 times
-
📄 2023: “Iterative Training Attack: A Black‑Box Adversarial Attack via Perturbation Generative Network” (J. of Circuits, Systems and Computers) – DOI:10.1142/S0218126623503140; black-box generative adversarial method;
-
📄 2023: “A Survey of Trojan Attacks and Defense to Neural Networks” (under review at ACM Computing Surveys); comprehensive lifecycle review of Trojan threats
-
📄 2024: “Data Poisoning‑based Backdoor Attack Framework against Supervised Learning Rules of Spiking Neural Networks” (submitted to IJCAI ’25); extends backdoor threats to spiking neural models