Mingyan Liu

Generating Adversarial Examples with Adversarial Networks

2018 · arXiv (Cornell University)

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples resulting from adding small-magnitude perturbations to inputs. Such adversarial examples can mislead DNNs to produce adversary-selected results. Different attack strategies have been …

Aggregate Cyber-Risk Management in the IoT Age: <i>Cautionary Statistics for (Re)Insurers and Likes</i>

2020 · IEEE Internet of Things Journal

IoT-driven smart societies are modern service-networked ecosystems, whose proper functioning is hugely based on the success of supply chain relationships. Robust security is still a big challenge in such ecosystems, catalyzed primarily by naive cyber-security …