26 citations · 44 across the 3 of their papers we have counts for
3 papers
cs.LG2021★ 26 cited
Exposing Previously Undetectable Faults in Deep Neural Networks
Isaac Dunn, Hadrien Pouget, Daniel Kroening +1
Existing methods for testing DNNs solve the oracle problem by constraining the raw features (e.g. image pixel values) to be within a small distance of a dataset example for which t…
cs.CV2020★ 9 cited
Evaluating Robustness to Context-Sensitive Feature Perturbations of Different Granularities
Isaac Dunn, Laura Hanu, Hadrien Pouget +2
We cannot guarantee that training datasets are representative of the distribution of inputs that will be encountered during deployment. So we must have confidence that our models d…
cs.LG2019★ 9 cited
Adaptive Generation of Unrestricted Adversarial Inputs
Isaac Dunn, Hadrien Pouget, Tom Melham +1
Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some n…