BYR Achieve · 镜像论坛

### 个人介绍李鑫峰博士，2019年和2024年从浙江大学获得学士和博士（with Honor）。目前在南洋理工大学担任博后研究员 ([https://letterligo.github.io/](https://letterligo.github.io/))，专注于多模态大模型、Agent的安全与隐私问题，以及LLM for 系统安全方面的研究。已在这些领域取得一系列成果，共发表安全四大顶会16篇，其中一作发表5篇。 ### 课题组与导师介绍： XiaoFeng Wang教授 (IEEE Fellow、ACM Fellow及AAAS Fellow获得者) 是计算机安全领域最知名学者之一，担任ACM SIGSAC主席。王教授是南洋理工大学杰出访问教授、美国印第安纳大学James H. Rudy Professor, 个人在计算机安全CS ranking方向排名世界第一，在安全四大顶级会议上的论文发表数量同样居于世界首位。 Dr. Wang is the Chair of ACM Special Interest Group on Security, Audit and Control (SIGSAC), and was also TPC Co-Chair of the ACM Conference on Computer and Communications Security (CCS), the ACM’s flagship security and privacy conference, during 2018 and 2019. In the past 20 years, Dr. Wang has been working on a broad range of research topics in systems security and data privacy. He is considered to be one of the most prominent systems security and privacy researchers, a top author according to online statistics such as [CSRanking](http://csrankings.org/#/index?sec), [System Security Circus (Eurecom)](https://www.s3.eurecom.fr/~balzarot/security-circus/index.html), and [Top Authors, the Systems Cirus (EPFL)](https://nebelwelt.net/pubstats/). Dr. Wang is known for his high-impact research on security analysis of real-world systems and biomedical data privacy. Particularly, the projects he led on side-channel analysis and mitigation, payment and single-sign-on API integrations, Android and iOS security and IoT protection have changed the way the industry built computing systems. Also he is a pioneer researcher on human genome privacy and a co-founder of the iDASH Genome Privacy Competition that contributes to reducing the gap between security and cryptography research and real-world demands for biomedical data sharing and computing protection. More recently, he is actively working on TEE-based Data-in-Use protection for supporting AI, Trustworthy AI, and application of AI technologies (such as NLP and deep learning) to protect computing systems, LTE/5G networks in particular. ### 科研内容: 1. 调研MLLM, Post-Training, Reasoning, Agent/Safety方向的论文，并交流讨论idea 2. 根据idea开展实验，完善idea并参与论文的撰写工作。 3. 参与论文投稿的流程，包括rebuttal和返修。 ### 研究方向： 1. LLM/VLM 安全与隐私 2. LLM Agent 安全与隐私 3. AI4Sec，如利用LLM提升系统安全性（如代码生成/理解，LTE/5G协议漏洞分析） 4. TEE可信执行环境-enabled secure AI computation 5. 软件安全、安卓安全 6. Secure Machine Learning: DP for ML, AI, and LLMs ### 基本要求 - 有较强的复现/动手能力，熟悉主流的大模型以及框架 - 对发表高水平论文有强烈的愿望 - 有基本的文献阅读能力 - GPA专业前5% - 加分项: 有LLM security的项目经历;有极强的自驱力（主动沟通、主动思考、主动探索）;有论文发表经历 ### 收获 - 发表高质量论文并按照贡献署名 - 提供国内高校（浙大智能系统安全实验室/复旦计算机学院）的26年博士、硕士入学机会 - 提供海外高校（新二港五）博士、交流、访问机会或者推荐信 - 提供知名教授、学者指导合作机会有意者微信联系【lxf286451488】请将简历发送至xinfeng.li@ntu.edu.sg，并抄送给ydyjyazzh@gmail.com 邮件主题请注明“科研实习申请+姓名+学校+年级+专业+排名”。如“科研实习申请+张三+北邮+大三+计算机科学与技术+前1%”

【浙江大学/南洋理工大学 科研实习】VLM/Agent Sec & LLM4Sec

【浙江大学/南洋理工大学科研实习】VLM/Agent Sec & LLM4Sec