paper-with-me

Papers

Runtime Safety Monitoring of Deep Neural Networks for Perception: A Survey

2025-11-08 · Albert Schotschneider, Svetlana Pavlitska, J. Marius Zöllner arxiv

Deep neural networks (DNNs) are widely used in perception systems for safety-critical applications, such as autonomous driving and robotics. However, DNNs remain vulnerable to various safety concerns, including generalization errors, out-of-distribution (OOD) inputs, and adversarial attacks, which can lead to hazardous failures. This survey provides a comprehensive overview of runtime safety monitoring approaches, which operate in parallel to DNNs during inference to detect these safety concerns without modifying the DNN itself. We categorize existing methods into three main groups: Monitoring inputs, internal representations, and outputs. We analyze the state-of-the-art for each category, identify strengths and limitations, and map methods to the safety concerns they address. In addition, we highlight open challenges and future research directions.

📄 PDF Abstract BibTeX arXiv:2511.05982

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Driving

Similar Papers 제목 키워드 기반

Safety Monitoring of Machine Learning Perception Functions: a Survey

2024-12-09 · Raul Sena Ferreira, Joris Guérin, Kevin Delmas, Jérémie Guiochet 외

Machine Learning (ML) models, such as deep neural networks, are widely applied in autonomous systems to perform complex perception tasks. New dependability challenges arise when ML predictions are used in safety-critical…

Survey

Explaining Unreliable Perception in Automated Driving: A Fuzzy-based Monitoring Approach

2025-05-20 · Aniket Salvi, Gereon Weiss, Mario Trapp

Autonomous systems that rely on Machine Learning (ML) utilize online fault tolerance mechanisms, such as runtime monitors, to detect ML prediction errors and maintain safety during operation. However, the lack of human-i…

Benchmarking

Clinical Pathways as Safety Specifications for Physical AI in Hospital Wards

2026-07-22 · Gabriele Franchini, Giulio Mallardi, Michele De Carolis, Filippo Lanubile arxiv

Ensuring safety in Physical AI systems operating in real-world environments is a critical challenge, particularly in hospital wards where vulnerable patients, clinical staff, medical devices, and assistive robots coexist…

Clinical KnowledgeAnomaly Detection

A Method for the Runtime Validation of AI-based Environment Perception in Automated Driving System

2024-12-21 · Iqra Aslam, Abhishek Buragohain, Daniel Bamal, Adina Aniculaesei 외

Environment perception is a fundamental part of the dynamic driving task executed by Autonomous Driving Systems (ADS). Artificial Intelligence (AI)-based approaches have prevailed over classical techniques for realizing …

Autonomous Driving

Using Formal Models, Safety Shields and Certified Control to Validate AI-Based Train Systems

2024-11-21 · Jan Gruteser, Jan Roßbach, Fabian Vu, Michael Leuschel

The certification of autonomous systems is an important concern in science and industry. The KI-LOK project explores new methods for certifying and safely integrating AI components into autonomous trains. We pursued a tw…