AI Model Utilization Measurements For Finding Class Encoding Patterns
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Representation Improvement in Latent Space for Search-Based Testing of Autonomous Robotic Systems
On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression
COOOL: Challenge Of Out-Of-Label A Novel Benchmark for Autonomous Driving
CARLA2Real: a tool for reducing the sim2real gap in CARLA simulator
Context-Aware Full Body Anonymization using Text-to-Image Diffusion Models
Accurate Automatic 3D Annotation of Traffic Lights and Signs for Autonomous Driving
토론
이 논문과 연결된 포럼 글이 아직 없습니다.