Prof. Xingyu ZHAO from Wuhan University delivered a talk on “Deep Learning Robustness: From A System Reliability’s Perspective”

/in /by

This talk examines deep learning robustness from a system reliability perspective, arguing that robustness should not be studied as an isolated AI model property but in relation to higher-level system claims such as safety assurance, reliability assessment, and security certification. It first reviews common robustness problem formulations, including binary robustness verification, maximum safe radius, maximum loss, and probabilistic robustness. Among these, probabilistic robustness is highlighted as especially relevant for safety-critical AI systems because it quantifies the likelihood of adversarial examples under stochastic perturbations, thereby aligning more naturally with reliability and risk reasoning in real-world operation.

The talk then distinguishes the roles of adversarial robustness and probabilistic robustness at system level. Adversarial robustness is more closely associated with security against maliciously optimized attacks, whereas probabilistic robustness better captures reliability and safety risks arising from benign operational noise, environmental uncertainty, and unsophisticated random perturbations. This distinction motivates a broader research agenda in which robustness metrics are selected according to the system-level property being claimed.

Building on this perspective, the talk presents the presenter team’s recent work on probabilistic robustness estimation, improvement and benchmarking. The talk advocates integrating probabilistic robustness into system-level safety and reliability modelling to support more meaningful assurance arguments for AI-enabled systems.

Read more

Prof. Zhaojun Li from Western New England University delivered a talk on “Reliability Modeling and Optimization of New Product Development (NPD) Process”

/in /by

The development of complex engineering products often needs to overcome many challenges such as meeting the development budget, release time, and performance goals. The new product development processes have been experiencing such challenges in an increasingly competitive global market environment. Specifically, the reliability of the new product has always been a major concern for new product developers, and it has been a difficulty to balance the development cost and time while sustaining high product reliability.

The main goal of this talk is to develop methodologies that help new product developers meet the product requirements and strategic business goals. This research consists of two main parts. In the first part, a novel methodology in modeling and optimizing the reliability growth is proposed, which considers the multiple stages of a new product development process and provides an optimal reliability growth plan in terms of time, cost, and the reliability of the newly developed products. The proposed approach differs from the existing research in the literature by, (1) considering multiple stages of the reliability growth program in the early stages of the new product development process, and (2) optimizing all three new product development goals simultaneously. The second part of this research provides an innovative approach to model and optimize the planning of a verification and validation (V&V) process in the early stages when designing a new product. This mathematical approach provides an optimal way of implementing a design verification and validation process to have maximum reliability improvement of a new product under development, when the implementation time and cost are limited.

Read more

Research paper accepted by IEEE Transactions on Reliability

/in /by

In this paper, we develop a data-efficient learning-based approach for accurately estimating the time-varying kinematic reliability of mechanisms. To improve data efficiency, we develop an adaptive sampling scheme that is guided by the prediction uncertainty of the resultant deep learning model. Overall, the proposed methodology follows a four-step procedure. First, a spectral-normalized neural Gaussian process (SNGP) is employed to quantify the prediction uncertainty of the deep learning model used to evaluate the time-varying kinematic reliability of mechanisms. Unlike other uncertainty quantification methods, SNGP has two unique characteristics: SNGP normalizes the weights of hidden layers of neural network to preserve the relative distances among samples during data transformation; SNGP replaces the conventional dense output layer of neural network with a random Fourier features-based Laplace approximation of Gaussian process for distance-aware uncertainty quantification. Next, based upon the uncertainty estimated by SNGP, we devise an active learning function to adaptively identify and select the most valuable next data sample to add to the training set. Thirdly, based on a predefined data acquisition metric, we iteratively add data points that maximize the active learning function to the training set and continue updating the deep learning model until a termination condition is met. Finally, we benchmark the developed approach for time-varying reliability analysis of mechanisms against Monte Carlo simulation, PHI2, and the Monte Carlo dropout-based uncertainty quantification method in terms of estimation accuracy and computational efficiency using three numerical examples. Computational results suggest that the developed method substantially reduces the number of performance function evaluations while achieving reliability estimates that are more accurate than those from MC dropout and comparable to those from MCS and PHI2.

Read more