![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
An overview of structural coverage metrics for testing neural networks
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. In this article, we provide...
-
Chapter and Conference Paper
QNNRepair: Quantized Neural Network Repair
We present QNNRepair, the first method in the literature for repairing quantized neural networks (QNNs). QNNRepair aims to improve the accuracy of a neural network model after quantization. It accepts the full...
-
Chapter and Conference Paper
Correction to: Rule-Based Runtime Mitigation Against Poison Attacks on Neural Networks
In an older version of this paper, there was error in the figure 3, (e) and (f) was incorrect. This has been corrected.
-
Chapter and Conference Paper
Rule-Based Runtime Mitigation Against Poison Attacks on Neural Networks
Poisoning or backdoor attacks are well-known attacks on image classification neural networks, whereby an attacker inserts a trigger into a subset of the training data, in such a way that the network learns to ...
-
Chapter and Conference Paper
NNrepair: Constraint-Based Repair of Neural Network Classifiers
We present NNrepair, a constraint-based technique for repairing neural network classifiers. The technique aims to fix the logic of the network at an intermediate layer or at the last layer. NNrepair first uses fa...
-
Chapter and Conference Paper
Building Better Bit-Blasting for Floating-Point Problems
An effective approach to handling the theory of floating-point is to reduce it to the theory of bit-vectors. Implementing the required encodings is complex, error prone and requires a deep understanding of flo...