67 citations · 299 across the 33 of their papers we have counts for
7 papers · 1 filter
SkipFuzz: Active Learning-based Input Selection for Fuzzing Deep Learning Libraries
Hong Jin Kang, Pattarakrit Rattanukul, Stefanus Agus Haryono +4
Many modern software systems are enabled by deep learning libraries such as TensorFlow and PyTorch. As deep learning is now prevalent, the security of deep learning libraries is a…
An Overview of Structural Coverage Metrics for Testing Neural Networks
Muhammad Usman, Youcheng Sun, Divya Gopinath +3
Deep neural network (DNN) models, including those used in safety-critical domains, need to be thoroughly tested to ensure that they can reliably perform well in different scenarios…
Toward Certified Robustness Against Real-World Distribution Shifts
Haoze Wu, Teruhiro Tagomori, Alexander Robey +6
We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts. To do so, we bridge the gap between hand-crafted specifications…
On the Perils of Cascading Robust Classifiers
Ravi Mangal, Zifan Wang, Chi Zhang +3
Ensembling certifiably robust neural networks is a promising approach for improving the \emph{certified robust accuracy} of neural models. Black-box ensembles that assume only quer…
VPN: Verification of Poisoning in Neural Networks
Youcheng Sun, Muhammad Usman, Divya Gopinath +1
Neural networks are successfully used in a variety of applications, many of them having safety and security concerns. As a result researchers have proposed formal verification tech…
Discrete-Event Controller Synthesis for Autonomous Systems with Deep-Learning Perception Components
Radu Calinescu, Calum Imrie, Ravi Mangal +4
We present DeepDECS, a new method for the synthesis of correct-by-construction discrete-event controllers for autonomous systems that use deep neural network (DNN) classifiers for…
AntidoteRT: Run-time Detection and Correction of Poison Attacks on Neural Networks
Muhammad Usman, Youcheng Sun, Divya Gopinath +1
We study backdoor poisoning attacks against image classification networks, whereby an attacker inserts a trigger into a subset of the training data, in such a way that at test time…