Mutation-Based Deep Learning Framework Testing Method in JavaScript Environment
This program is tentative and subject to change.
In recent years, Deep Learning (DL) applications in JavaScript environment have become increasingly popular. As the infrastructure for DL applications, JavaScript DL frameworks play a crucial role in the development and deployment. It is essential to ensure the quality of JavaScript DL frameworks. However, the bottleneck of limited computational resources in the JavaScript environment brings new challenges to framework testing. Specifically, JavaScript DL frameworks equips with various optimization mechanisms (e.g., cache reuse, inference acceleration) to overcome the bottleneck of limited computational resources. These optimization mechanisms are overlooked by existing methods, resulting in many bugs in JavaScript DL frameworks being missed. To address the above challenges, we propose a mutation-based JavaScript DL framework testing method named DLJSFuzzer. DLJSFuzzer designs 13 tensor mutation rules targeting the cache reuse mechanism to generate test input tensors. Besides, DLJSFuzzer designs eight model mutation rules targeting the inference acceleration mechanism to generate test input models. To evaluate the effectiveness of DLJSFuzzer, we conduct experiments on the most widely-used JavaScript DL framework, TensorFlow.js. The experimental results show that DLJSFuzzer outperforms state-of-the-art methods in both effectiveness and efficiency. DLJSFuzzer successfully detects 21 unique crashes and 126 unique NaN & Inconsistency bugs. All detected crashes have been reported to the open-source community, with 12 of them already confirmed by developers. Additionally, DLJSFuzzer has improved by over 47% in model generation efficiency and over 91% in bug detection efficiency compared to all baselines.
This program is tentative and subject to change.
Thu 31 OctDisplayed time zone: Pacific Time (US & Canada) change
15:30 - 16:30 | |||
15:30 15mTalk | DevMuT: Testing Deep Learning Framework via Developer Expertise-Based Mutation Research Papers Yanzhou Mu , Juan Zhai University of Massachusetts at Amherst, Chunrong Fang Nanjing University, Xiang Chen Nantong University, Zhixiang Cao , Peiran Yang State Key Laboratory for Novel Software Technology, Nanjing University, China, Yinglong Zou Nanjing University, Tao Zheng Nanjing University, Zhenyu Chen Nanjing University | ||
15:45 15mTalk | Mutation-Based Deep Learning Framework Testing Method in JavaScript Environment Research Papers Yinglong Zou Nanjing University, Juan Zhai University of Massachusetts at Amherst, Chunrong Fang Nanjing University, Jiawei Liu University of Illinois at Urbana-Champaign, Tao Zheng Nanjing University, Zhenyu Chen Nanjing University | ||
16:00 15mTalk | DynaMO: Protecting Mobile DL Models through Coupling Obfuscated DL Operators Research Papers Mingyi Zhou Monash University, Xiang Gao Beihang University, Xiao Chen University of Newcastle, Chunyang Chen TU Munich, John Grundy Monash University, Li Li Beihang University | ||
16:15 15mTalk | GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models Research Papers Zhibo Zhang Huazhong University of Science and Technology, Wuxia Bai Huazhong University of Science and Technology, Yuxi Li Huazhong University of Science and Technology, Mark Huasong Meng National University of Singapore, Kailong Wang Huazhong University of Science and Technology, Ling Shi Nanyang Technological University, Li Li Beihang University, Jun Wang Post Luxembourg, Haoyu Wang Huazhong University of Science and Technology | ||