This work addresses the problems of (a) designing utilization measurements of trained artificial intelligence (AI) models and (b) explaining how training data are encoded in AI models based on those measurements. The problems are motivated by the lack of explainability of AI models in security and safety critical applications, such as the use of AI models for classification of traffic signs in self-driving cars. We approach the problems by introducing theoretical underpinnings of AI model utilization measurement and understanding patterns in utilization-based class encodings of traffic signs at the level of computation graphs (AI models), subgraphs, and graph nodes. Conceptually, utilization is defined at each graph node (computation unit) of an AI model based on the number and distribution of unique outputs in the space of all possible outputs (tensor-states). In this work, utilization measurements are extracted from AI models, which include poisoned and clean AI models. In contrast to clean AI models, the poisoned AI models were trained with traffic sign images containing systematic, physically realizable, traffic sign modifications (i.e., triggers) to change a correct class label to another label in a presence of such a trigger. We analyze class encodings of such clean and poisoned AI models, and conclude with implications for trojan injection and detection.
Missing Pattern Tree based Decision Grouping and Ensemble for Enhancing Pair Utilization in Deep Incomplete Multi-View Clustering
School of Computer Science and Engineering, University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院);Department of Computer Science and Engineering, Lehigh University(莱斯大学计算机科学与工程系);Department of Computer Science, University of Illinois Chicago(伊利诺伊大学芝加哥分校计算机科学系);School of Computer Science and Technology, Hainan University(海南大学计算机科学与技术学院)
Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution
Baidu Research(百度研究院);Zhejiang University(浙江大学);Tsinghua University(清华大学);China Longyuan Power Group Corp. Ltd.(中国龙源电力集团股份有限公司);Dalian University of Technology(大连理工大学)
Comprehensive Analysis of VQC for Financial Fraud Detection: A Comparative Study of Quantum Encoding Techniques and Architectural Optimizations
School of Science;Engineering, Al Akhawayn University, Ifrane, Morocco.;Engineering Sciences Laboratory,Polydisciplinary Faculty of Taza, Sidi Mohamed Ben Abdellah University, Fez, Morocco.;Signal Systems \& Components Laboratory, Faculty of Sciences;Technology, Sidi Mohamed Ben Abdellah University, Fez, Morocco.;University of Medina Saudi Arabia, Kingdom of Saudi Arabia