DeepExploitor: LLM-Enhanced Automated Exploitation of DeepLink Attack in Hybrid Apps
This program is tentative and subject to change.
Modern mobile apps widely embed WebView to enable rich and dynamic content, making it an increasingly attractive target for attackers. It is well known that insufficient or improper input validation on WebView-loaded URLs can compromise the entire app or even the underlying system. Among these threats, one of the most critical attack vectors is the DeepLink Attack, which often requires only a single user click to exploit WebView vulnerabilities. Despite the deployment of defense such as URL allowlists, misconfigurations and inconsistent implementations continue to expose apps to exploitation. In this paper, we present DeepExploitor, the first automated exploit generation framework targeting vulnerabilities exploitable via DeepLink Attack. DeepExploitor addresses two key challenges: First, it statically models complex, app-specific routing encapsulation and customized deep link parsing logic by slicing constraint-related code and resolving them through large language models (LLMs), enabling scalable discovery of valid exploit formats. Second, it identifies and mutates trusted domains embedded in the app to bypass black-box defenses such as domain-based allowlists. We evaluated DeepExploitor on 433 of the most popular Android apps and uncovered 83 zero-day vulnerabilities, including 24 rated as high or critical severity. All findings were responsibly disclosed to affected vendors, with 35 acknowledged to date or assigned CVE/CNVD identifiers.
This program is tentative and subject to change.
Tue 18 NovDisplayed time zone: Seoul change
11:00 - 12:30 | |||
11:00 10mTalk | Vulnerability-Affected Versions Identification: How Far Are We? Research Papers Xingchu Chen Institute of Information Engineering, CAS; School of Cyber Security, UCAS, Chengwei Liu Nanyang Technological University, Jialun Cao Hong Kong University of Science and Technology, Yang Xiao Chinese Academy of Sciences, Xinyue Cai Institute of Information Engineering at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Yeting Li Institute of Information Engineering at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Jingyi Shi Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, tianqi sun Institute of Information Engineering, Chinese Academy of Sciences, Haiming Chen Institute of Software, Chinese Academy of Sciences, Wei Huo Institute of Information Engineering at Chinese Academy of Sciences | ||
11:10 10mTalk | LOSVER: Line-Level Modifiability Signal-Guided Vulnerability Detection and Classification Research Papers Doha Nam Korea Advanced Institute of Science and Technology, Jongmoon Baik Korea Advanced Institute of Science and Technology | ||
11:20 10mTalk | VERCATION: Precise Vulnerable Open-source Software Version Identification based on Static Analysis and LLM Journal-First Track Yiran Cheng Beijing Key Laboratory of IOT Information Security Technology, Institute of Information Engineering, CAS, Beijing, China; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, Chinaï¼›, Ting Zhang Monash University, Lwin Khin Shar Singapore Management University, Shouguo Yang Zhongguancun Laboratory, Beijing, China, Chaopeng Dong Institute of Information Engineering, CAS, Beijing, China; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China;, David Lo Singapore Management University, Shichao Lv Institute of Information Engineering at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Zhiqiang Shi Institute of Information Engineering at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Limin Sun Institute of Information Engineering at Chinese Academy of Sciences; University of Chinese Academy of Sciences | ||
11:30 10mTalk | Not Every Patch is an Island: LLM-Enhanced Identification of Multiple Vulnerability Patches Research Papers Yi Song School of Computer Science, Wuhan University, Dongchen Xie School of Cyber Science and Engineering, Wuhan University, Lin Xu School of Cyber Science and Engineering, Wuhan University, He Zhang School of Computer Science, Wuhan University, Chunying Zhou School of Computer Science, Wuhan University, Xiaoyuan Xie Wuhan University | ||
11:40 10mTalk | Vul-R2: A Reasoning LLM for Automated Vulnerability Repair Research Papers Xin-Cheng Wen Harbin Institute of Technology, Zirui Lin Harbin Institute of Technology, Shenzhen, Yijun Yang Tencent AI Lab, Cuiyun Gao Harbin Institute of Technology, Shenzhen, Deheng Ye Tencent AI Lab | ||
11:50 10mTalk | DeepExploitor: LLM-Enhanced Automated Exploitation of DeepLink Attack in Hybrid Apps Research Papers Zhangyue Zhang Fudan University, Lei Zhang Fudan University, Zhibo Zhang Huazhong University of Science and Technology, Yongheng Liu Fudan University, Zhemin Yang Fudan University, Yuan Zhang Fudan University, Min Yang Fudan University | ||
12:00 10mTalk | Demystifying Cookie Sharing Risks in WebView-based Mobile App-in-app Ecosystems Research Papers Miao Zhang Beijing University of Posts and Telecommunications, Shenao Wang Huazhong University of Science and Technology, Guilin Zheng Beijing University of Posts and Telecommunications, Yanjie Zhao Huazhong University of Science and Technology, Haoyu Wang Huazhong University of Science and Technology | ||
12:10 10mTalk | Hit The Bullseye On The First Shot: Improving LLMs Using Multi-Sample Self-Reward Feedback for Vulnerability Repair Research Papers Rui Jiao Xidian University, Yue Zhang Drexel University, Jinku Li Xidian University, Jianfeng Ma Xidian University | ||
12:20 10mTalk | Propagation-Based Vulnerability Impact Assessment for Software Supply Chains Research Papers Bonan Ruan National University of Singapore, Zhiwei Lin National University of Singapore, Jiahao Liu National University of Singapore, Chuqi Zhang National University of Singapore, Kaihang Ji National University of Singapore, Zhenkai Liang National University of Singapore Pre-print | ||