Nadarajah Asokan

TL;DR: Today, cross-device communication and intelligent resource sharing among smart devices is limited and inflexible: Typically devices cooperate using fixed interfaces provided by custom-built applications, which users need to install manually.

TL;DR: This work presents a novel attestation scheme that bootstraps from existing application certification infrastructures available on mobile device platforms, and thus avoids the need to setup and maintain a new service that provides translation from software measurements to properties, and consequently makes realization of property-based attestation economically feasible.

TL;DR: Two complementary approaches for making context-based PoPs resilient to malicious provers are proposed: one approach focuses on surprisal filtering based on estimating the entropy of particular PoPs in order to detect context measurements vulnerable to such attacks, and the other is based on utilizing longitudinal observations of ambient modalities like noise level and ambient luminosity.

TL;DR: WAFFLE is presented, the first approach to watermark DNN models trained using federated learning, which efficiently embeds a resilient watermark into models incurring only negligible degradation in test accuracy, and does not require access to training data.

TL;DR: Zhang et al. as mentioned in this paper investigated a prominent zero-effort deauthentication scheme, called ZEBRA, which provides an interesting and a useful solution to a difficult problem as demonstrated in the original paper and identified a subtle incorrect assumption in its adversary model that leads to a fundamental design flaw.