Certifiable robustness, the functionality of verifying whether the given region surrounding a
data point admits any adversarial example, provides guaranteed security for neural …

One intriguing property of deep neural networks (DNNs) is their vulnerability to adversarial
examples–those maliciously crafted inputs that deceive target DNNs. While a plethora of …

High sensitivity of neural networks against malicious perturbations on inputs causes security
concerns. To take a steady step towards robust classifiers, we aim to create neural network …

The efficient and accurate characterization of the robustness of neural networks to input
perturbation is an important open problem. Many approaches exist including heuristic and …

Neural networks have been widely applied in security applications such as spam and
phishing detection, intrusion prevention, and malware detection. This black-box method …

Despite the functional success of deep Neural Networks, their trustworthiness remains a
crucial open challenge. To address this challenge, both testing and verification techniques …

Verifying robustness of neural network classifiers has attracted great interests and attention
due to the success of deep neural networks and their unexpected vulnerability to adversarial …

Deployment of deep neural networks (DNNs) in safety-critical systems requires provable
guarantees for their correct behaviours. We compute the maximal radius of a safe norm ball …

In response to subtle adversarial examples flipping classifications of neural network models,
recent research has promoted certified robustness as a solution. There, invariance of …

Neural networks are commonly used in safety-critical real-world applications. Unfortunately,
the predicted output is often highly sensitive to small, and possibly imperceptible, changes to …