activity
20092023
most citedNeural Networks for Safety-Critical Applications - Challenges, Experiments and Perspectives

7 citations · 19 across the 12 of their papers we have counts for

collaborators

24 papers

cs.LG2023

Towards Rigorous Design of OoD Detectors

Chih-Hong Cheng, Changshun Wu, Harald Ruess +1

Out-of-distribution (OoD) detection techniques are instrumental for safety-related neural networks. We are arguing, however, that current performance-oriented OoD detection techniq…

cs.CV2022

Butterfly Effect Attack: Tiny and Seemingly Unrelated Perturbations for Object Detection

Nguyen Anh Vu Doan, Arda Yüksel, Chih-Hong Cheng

This work aims to explore and identify tiny and seemingly unrelated perturbations of images in object detection that will lead to performance degradation. While tininess can natura…

cs.SE2022

Facilitating Change Implementation for Continuous ML-Safety Assurance

Chih-Hong Cheng, Nguyen Anh Vu Doan, Balahari Balu +9

We propose a method for deploying a safety-critical machine-learning component into continuously evolving environments where an increased degree of automation in the engineering pr…

cs.SE2022

Prioritizing Corners in OoD Detectors via Symbolic String Manipulation

Chih-Hong Cheng, Changshun Wu, Emmanouil Seferis +1

For safety assurance of deep neural networks (DNNs), out-of-distribution (OoD) monitoring techniques are essential as they filter spurious input that is distant from the training d…

cs.LG2022

Unaligned but Safe -- Formally Compensating Performance Limitations for Imprecise 2D Object Detection

Tobias Schuster, Emmanouil Seferis, Simon Burton +1

In this paper, we consider the imperfection within machine learning-based 2D object detection and its impact on safety. We address a special sub-type of performance limitations: th…

cs.RO2021

ComOpT: Combination and Optimization for Testing Autonomous Driving Systems

Changwen Li, Chih-Hong Cheng, Tiantian Sun +2

ComOpT is an open-source research tool for coverage-driven testing of autonomous driving systems, focusing on planning and control. Starting with (i) a meta-model characterizing di…