As cloud tenants increasingly adopt ARM servers, securing their sensitive workloads becomes a critical concern. Confidential virtualization, which shields data from privileged software by establishing isolated VMs, has emerged as a standard approach to address this concern. However, ARM's official solution, the Confidential Compute Architecture (CCA), fails to meet this demand. It lacks support on most deployed hardware, and its widespread adoption by major cloud providers remains distant. In this paper, we propose TwinVisor, a novel system that enables confidential virtualization on ARM platforms. TwinVisor innovatively retrofits the mature ARM TrustZone to enforce strong isolation for confidential VMs, while minimizing the TCB by decoupling resource management from security mechanisms. Specifically, TwinVisor introduces a tiny hypervisor in the secure world (calledS-visorin this paper) dedicated to protection, while reusing a full-fledged hypervisor (calledN-visor) in the normal world for resource management. By combining S-EL2 hardware virtualization features with software-based same-privilege protection techniques, TwinVisor achieves broad compatibility, enabling its deployment on almost all ARM platforms. We have implemented two prototypes of TwinVisor, and our evaluation demonstrates that it can effectively protect confidential VMs while imposing negligible performance overhead for real-world applications.

To enable situational awareness for automated driving in intelligent transportation systems (ITS), it is envisioned that vehicles will be equipped with sensors, and possibly perform collaborative sensing amongst themselves. Unfortunately such sensing is subject to obstructions, e.g., other vehicles, and the performance can be poor when the penetration of collaborating vehicles is low. A possible solution is to deploy sensing and communication capable infrastructure, e.g., road side units (RSUs) and base stations (BSs), to assist collaborative sensing. This paper explores the performance of infrastructure assisted sensing of roads under various deployment schemes. Our analytical results show that deploying RSUs at intersections and at even spacings is most efficient in covering the roads while cellular based sensors may subject to building obstructions and should be located along roads working as RSUs. RSUs located above the vehicles can have 100% coverage of vehicles once the communication range is large enough to reach relevant sensors. Infrastructure provides a second advantage in providing a dynamic view of the road and thus better coverage over time. Such benefit from sensing temporal diversity is shared by vehicles moving in the opposite direction, yet collaborating with such vehicles involves more challenging V2V communication given the high relative speed and obstruction unless leveraging V2I relays.

Wireless channels in millimeter wave based wearable networks are particularly susceptible to environmental blockages and dynamics when there are humans/objects in motion. Such dynamics imply, not only physical layer overheads to discover and track viable transmission paths, but also MAC overheads to keep track of neighboring interferers, perform clustering and enable proper scheduling of transmissions. We shall focus on overheads at timescale associated with the latter. This paper introduces a stochastic geometric model to study the impact of mobility on overheads in such networks. We provide a complete characterization of the temporal dynamics of strong interference channels resulting from blocking in networks comprising both fixed and mobile nodes. We show the state of a channel, Line-of-Sight(LOS)/Non-LOS(NLOS), follows an on/off renewal process and derive the associated distributions. Our model further enables us to evaluate how the overall rate of change for the set of strong LOS interferers seen by a fixed user scales with user density and proportion of mobile users. The overhead to track the interference environment may in fact be limited with user density but increases with proportion of mobile users. In a highly mobile environment, the changes in channels are frequent and the overheads for coordination become high, with distant and/or mobile users requiring more overheads. Based on our results, we suggest fixed users may coordinate with close by neighbors while mobile users are better off resorting to simpler ad hoc MACs.

MmWave based wearable networks will need to function in various environments including possibly high density settings, e.g., train cars. At such densities one might expect challenges in interference management and/or excessive overheads tracking and jointly scheduling interferers. In this paper we use simple stochastic geometric models to examine the characteristics (number and sensitivity to motion) of "strong interferers" and show that due to blocking they are not monotonic in user density. Indeed, perhaps surprisingly, the most challenging setting appears to arise at "intermediate" user densities. We then propose a simple model to evaluate the performance of current MAC designs based on clustering and hierarchical scheduling. The results exhibit a performance trade-off leading to an optimal cluster size which depends on the directionality of transmissions. More importantly, we show that at high densities the per user throughput is roughly constant, suggesting wearable networks will scale well in dense scenarios.

State-of-the-art D2D schedulers' performance can be evaluated from at least two different perspectives: the sum throughput and the fraction of satisfied users/applications. In this paper we revisit the performance of such schedulers, e.g., FlashLinQ/ITLinQ, showing they strike particular trade-offs between these two metrics. Our analysis and simulations show that the sum-rate benefits of such schedulers come at the expense of fairness, which under high densities can lead to a substantial fraction of unsatisfied users. This motivates a proposed opportunistic scheduler design, Binary Quantile (BQ) scheduling, which further exploits temporal channel variations via a low overhead distributed mechanisms and realizes substantial improvements in user/application performance. We further show that an adapting version of BQ scheduling where link quantile thresholds are adjusted based on achieved throughput can further achieve substantial improvement in user/application level satisfaction which is robust to heterogeneity in the network topology.