Deep learning models have shown promising predictive accuracy for time-s...
Deep neural networks (DNN) have become a common sensing modality in
auto...
Deep neural networks have emerged as the workhorse for a large section o...
Although organizations are continuously making concerted efforts to hard...
Adversarial training (AT) and its variants have spearheaded progress in
...
This paper tackles the problem of making complex resource-constrained
cy...
Environments with sparse rewards and long horizons pose a significant
ch...
High-quality labels are expensive to obtain for many machine learning ta...
Improving adversarial robustness of neural networks remains a major
chal...
This paper presents ModelGuard, a sampling-based approach to runtime mod...
As machine learning techniques become widely adopted in new domains,
esp...
Providing reliable model uncertainty estimates is imperative to enabling...
Reliable uncertainty estimates are an important tool for helping autonom...
Deep neural network (DNN) models have proven to be vulnerable to adversa...
Cyberphysical systems (CPS) are ubiquitous in our personal and professio...
This paper describes a verification case study on an autonomous racing c...
Industrial cyber-physical systems are hybrid systems with strict safety
...
Data-driven techniques are used in cyber-physical systems (CPS) for
cont...