6 papers
Catalyst: Out-of-Distribution Detection via Elastic Scaling
Abid Hassan, Tuan Ngo, Saad Shafiq +1
Out-of-distribution (OOD) detection is critical for the safe deployment of deep neural networks. State-of-the-art post-hoc methods typically derive OOD scores from the output logit…
DAVIS: OOD Detection via Dominant Activations and Variance for Increased Separation
Abid Hassan, Tuan Ngo, Saad Shafiq +1
Detecting out-of-distribution (OOD) inputs is a critical safeguard for deploying machine learning models in the real world. However, most post-hoc detection methods operate on penu…
DNN Modularization via Activation-Driven Training
Tuan Ngo, Abid Hassan, Saad Shafiq +1
Deep Neural Networks (DNNs) tend to accrue technical debt and suffer from significant retraining costs when adapting to evolving requirements. Modularizing DNNs offers the promise…
Identifying Appropriately-Sized Services with Deep Reinforcement Learning
Syeda Tasnim Fabiha, Saad Shafiq, Wesley Klewerton Guez Assunção +1
Service-based architecture (SBA) has gained attention in industry and academia as a means to modernize legacy systems. It refers to a design style that enables systems to be develo…
Are We Learning the Right Features? A Framework for Evaluating DL-Based Software Vulnerability Detection Solutions
Satyaki Das, Syeda Tasnim Fabiha, Saad Shafiq +1
Recent research has revealed that the reported results of an emerging body of DL-based techniques for detecting software vulnerabilities are not reproducible, either across differe…
Toward Improved Deep Learning-based Vulnerability Detection
Adriana Sejfia, Satyaki Das, Saad Shafiq +1
Deep learning (DL) has been a common thread across several recent techniques for vulnerability detection. The rise of large, publicly available datasets of vulnerabilities has fuel…