Search

Federated Graph Neural Network (FedGNN) is a privacy-preserving machine learning technology that combines federated learning (FL) and graph neural networks (GNNs). It offers a privacy-preserving solution for training GNNs using isolated graph data. Vertical Federated Graph Neural Network (VFGNN) is an important branch of FedGNN, where data features and labels are distributed among participants, and each participant has the same sample space. Due to the difficulty of accessing and modifying distributed data and labels, the vulnerability of VFGNN to backdoor attacks remains largely unexplored. In this context, we propose BVG, the first method for backdoor attacks in VFGNN. Without accessing or modifying labels, BVG uses multi-hop triggers and requires only four target class nodes for an effective backdoor attack. Experiments show that BVG achieves high attack success rates (ASR) across three datasets and three different GNN models, with minimal impact on main task accuracy (MTA). We also evaluate several defense methods, further validating the robustness and effectiveness of BVG. This finding also highlights the need for advanced defense mechanisms to counter sophisticated backdoor attacks in practical VFGNN applications.

Acoustic-sensor-based soft error resilience is particularly promising, since it can verify the absence of soft errors and eliminate silent data corruptions at a low hardware cost. However, the state-of-the-art work incurs a significant performance overhead for in-order cores due to frequent structural/data hazards during the verification. To address the problem, this paper presents Turnpike, a compiler/architecture co-design scheme that can achieve lightweight yet guaranteed soft error resilience for in-order cores. The key idea is that many of the data computed in the core can bypass the soft error verification without compromising the resilience. Along with simple microarchitectural support for realizing the idea, Turnpike leverages compiler optimizations to further reduce the performance overhead. Experimental results with 36 benchmarks demonstrate that Turnpike only incurs a 0-14% run-time overhead on average while the state-of-the-art incurs a 29-84% overhead when the worst-case latency of the sensor based error detection is 10-50 cycles., Comment: 13 pages and 26 figures

Energy harvesting systems have shown their unique benefit of ultra-long operation time without maintenance and are expected to be more prevalent in the era of Internet of Things. However, due to the batteryless nature, they suffer unpredictable frequent power outages. They thus require a lightweight mechanism for crash consistency since saving/restoring checkpoints across the outages can limit forward progress by consuming hard-won energy. For the reason, energy harvesting systems have been designed with a non-volatile memory (NVM) only. The use of a volatile data cache has been assumed to be not viable or at least challenging due to the difficulty to ensure cacheline persistence. In this paper, we propose ReplayCache, a software-only crash consistency scheme that enables commodity energy harvesting systems to exploit a volatile data cache. ReplayCache does not have to ensure the persistence of dirty cachelines or record their logs at run time. Instead, ReplayCache recovery runtime re-executes the potentially unpersisted stores in the wake of power failure to restore the consistent NVM state, from which interrupted program can safely resume. To support store replay during recovery, ReplayCache partitions program into a series of regions in a way that store operand registers remain intact within each region, and checkpoints all registers just before power failure using the crash consistency mechanism of the commodity systems. For performance, ReplayCache enables region-level persistence that allows the stores in a region to be asynchronously persisted until the region ends, exploiting ILP. The evaluation with 23 benchmark applications show that compared to the baseline with no caches, ReplayCache can achieve about 10.72x and 8.5x-8.9x speedup (on geometric mean) for the scenarios without and with power outages, respectively., Comment: 13 pages and 19 figures

This paper considers the consensus performance improvement problem of networked general linear agents subject to external disturbances over Markovian randomly switching communication topologies. The consensus control laws can only use its local output information. Firstly, a class of full-order observer-based control protocols is proposed to solve this problem, which depends solely on the relative outputs of neighbours. Then, to eliminate the redundancy involved in the full-order observer, a class of reduced-order observer-based control protocols is designed. Algorithms to construct both protocols are presented, which guarantee that agents can reach consensus in the asymptotic mean square sense when they are not perturbed by disturbances, and that they have decent $H_{\infty}$ performance and transient performance when the disturbances exist. At the end of this manuscript, numerical simulations which apply both algorithms to four networked Raptor-90 helicopters are performed to verify the theoretical results.

Edge bundling methods can effectively alleviate visual clutter and reveal high-level graph structures in large graph visualization. Researchers have devoted significant efforts to improve edge bundling according to different metrics. As the edge bundling family evolve rapidly, the quality of edge bundles receives increasing attention in the literature accordingly. In this paper, we present MLSEB, a novel method to generate edge bundles based on moving least squares (MLS) approximation. In comparison with previous edge bundling methods, we argue that our MLSEB approach can generate better results based on a quantitative metric of quality, and also ensure scalability and the efficiency for visualizing large graphs., Comment: Appears in the Proceedings of the 25th International Symposium on Graph Drawing and Network Visualization (GD 2017)