Byzantine-Robust Federated Learning via Credibility Assessment on Non-IID Data

Federated learning is a novel framework that enables resource-constrained edge devices to jointly learn a model, which solves the problem of data protection and data islands. However, standard federated learning is vulnerable to Byzantine attacks, which will cause the global model to be manipulated by the attacker or fail to converge. On non-iid data, the current methods are not effective in defensing against Byzantine attacks. In this paper, we propose a Byzantine-robust framework for federated learning via credibility assessment on non-iid data (BRCA). Credibility assessment is designed to detect Byzantine attacks by combing adaptive anomaly detection model and data verification. Specially, an adaptive mechanism is incorporated into the anomaly detection model for the training and prediction of the model. Simultaneously, a unified update algorithm is given to guarantee that the global model has a consistent direction. On non-iid data, our experiments demonstrate that the BRCA is more robust to Byzantine attacks compared with conventional methods

Multi-objective Conflict-based Search Using Safe-interval Path Planning

This paper addresses a generalization of the well known multi-agent path finding (MAPF) problem that optimizes multiple conflicting objectives simultaneously such as travel time and path risk. This generalization, referred to as multi-objective MAPF (MOMAPF), arises in several applications ranging from hazardous material transportation to construction site planning. In this paper, we present a new multi-objective conflict-based search (MO-CBS) approach that relies on a novel multi-objective safe interval path planning (MO-SIPP) algorithm for its low-level search. We first develop the MO-SIPP algorithm, show its properties and then embed it in MO-CBS. We present extensive numerical results to show that (1) there is an order of magnitude improvement in the average low level search time, and (2) a significant improvement in the success rates of finding the Pareto-optimal front can be obtained using the proposed approach in comparison with the state of the art. Finally, we also provide a case study to demonstrate the potential application of the proposed algorithms for construction site planning.

Multi-Objective Path-Based D* Lite

Incremental graph search algorithms, such as D* Lite, reuse previous search efforts to speed up subsequent similar path planning tasks. These algorithms have demonstrated their efficiency in comparison with search from scratch, and have been leveraged in many applications such as navigation in unknown terrain. On the other hand, path planning typically involves optimizing multiple conflicting objectives simultaneously, such as travel risk, arrival time, etc. Multi-objective path planning is challenging as the number of Pareto-optimal solutions can grow exponentially with respect to the size of the graph, which makes it computationally burdensome to plan from scratch each time when similar planning tasks needs to be solved. This article presents a new multi-objective incremental search algorithm called Multi-Objective Path-Based D* Lite (MOPBD*) which reuses previous search efforts to speed up subsequent planning tasks while optimizing multiple objectives. Numerical results show that MOPBD* is more efficient than search from scratch and runs an order of magnitude faster than existing incremental method for multi-objective path planning.

Predicting Surface Heat Flux on Complex Systems via Conv-LSTM

Existing algorithms with iterations as the principle for 3D inverse heat conduction problems (IHCPs) are usually time-consuming. With the recent advancements in deep learning techniques, it is possible to apply the neural network to compute IHCPs. In this paper, a new framework based on Convolutional-LSTM is introduced to predict the transient heat flux via measured temperature. The inverse heat conduction models concerned in this work have 3D complex structures with non-linear boundary conditions and thermophysical parameters. In order to reach high precision, a forward solver based on the finite element method is utilized to generate sufficient data for training. The fully trained framework can provide accurate predictions efficiently once the measured temperature and models are acquired. It is believed that the proposed framework offers a new pattern for real-time heat flux inversion.

Semiconductor-metal phase transition and emergent charge density waves in 1T-ZrX$_2$ (X = Se, Te)

Charge density wave (CDW) is a collective quantum phenomenon in metals and features a wave-like modulation of the conduction electron density. A microscopic understanding and experimental control of this many-body electronic state in atomically thin materials remain hot topics in condensed matter physics. Here we report an interface and/or Zr intercalation induced semiconductor-metal phase transition, as well as a concomitant (2 $times$ 2) CDW order in 1T-ZrX$_2$ (X = Se, Te) thin films prepared on graphitized SiC(0001) substrates. Also observed has been a sizable CDW energy gap up to 22 meV opened at the Fermi level. Fourier-transformed scanning tunneling microscopy reveals a rather simple Fermi surface, consisting only of Zr 4d-derived conduction band at the corners of the Brillouin zone. Our finding that such a simple electronic structure is compatible with the CDW phase proves intriguing and challenges several prevailing scenarios for the formation of CDW in transition metal dichalcogenides.

Merohedral disorder and impurity impacts on superconductivity of fullerenes

Local quasiparticle states around impurities provide essential insight into the mechanism of unconventional superconductivity, especially when the candidate materials are proximate to an antiferromagnetic Mott-insulating phase. While such states have been reported in atom-based cuprates and iron-based compounds, they are unexplored in organic superconductors which feature tunable molecular orientation. Here we employ scanning tunneling microscopy and spectroscopy to reveal multiple forms of robustness of an exotic $s$-wave superconductivity in epitaxial Rb$_3$C$_{60}$ films against merohedral disorder, non-magnetic single impurities and step edges at the atomic scale. Also observed have been Yu-Shiba-Rusinov (YSR) states induced by deliberately incurred Fe adatoms that act as magnetic scatters. The bound states display abrupt spatial decay and vary in energy with the Fe adatom registry. Our results and the universal optimal superconductivity at half-filling point towards local electron pairing in which the multiorbital electronic correlations and intramolecular phonons together drive the high-temperature superconductivity of doped fullerenes.

Stoichiometry and defect superstructures in epitaxial FeSe films on SrTiO3

Cryogenic scanning tunneling microscopy is employed to investigate the stoichiometry and defects of epitaxial FeSe thin films on SrTiO3(001) substrates under various post-growth annealing conditions. Low-temperature annealing with an excess supply of Se leads to formation of Fe vacancies and superstructures, accompanied by a superconductivity (metal)-to-insulator transition in FeSe films. By contrast, high-temperature annealing could eliminate the Fe vacancies and superstructures, and thus recover the high-temperature superconducting phase of monolayer FeSe films. We also observe multilayer FeSe during low-temperature annealing, which is revealed to link with Fe vacancy formation and adatom migration. Our results document very special roles of film stoichiometry and help unravel several controversies in the properties of monolayer FeSe films.

How to Secure Distributed Filters Under Sensor Attacks

We study how to secure distributed filters for linear time-invariant systems with bounded noise under false-data injection attacks. A malicious attacker is able to arbitrarily manipulate the observations for a time-varying and unknown subset of the sensors. We first propose a recursive distributed filter consisting of two steps at each update. The first step employs a saturation-like scheme, which gives a small gain if the innovation is large corresponding to a potential attack. The second step is a consensus operation of state estimates among neighboring sensors. We prove the estimation error is upper bounded if the filter parameters satisfy a condition. We further analyze the feasibility of the condition and connect it to sparse observability in the centralized case. When the attacked sensor set is known to be time-invariant, the secured filter is modified by adding an online local attack detector. The detector is able to identify the attacked sensors whose observation innovations are larger than the detection thresholds. Also, with more attacked sensors being detected, the thresholds will adaptively adjust to reduce the space of the stealthy attack signals. The resilience of the secured filter with detection is verified by an explicit relationship between the upper bound of the estimation error and the number of detected attacked sensors. Moreover, for the noise-free case, we prove that the state estimate of each sensor asymptotically converges to the system state under certain conditions. Numerical simulations are provided to illustrate the developed results.

Adaptive Routing Between Capsules

Capsule network is the most recent exciting advancement in the deep learning field and represents positional information by stacking features into vectors. The dynamic routing algorithm is used in the capsule network, however, there are some disadvantages such as the inability to stack multiple layers and a large amount of computation. In this paper, we propose an adaptive routing algorithm that can solve the problems mentioned above. First, the low-layer capsules adaptively adjust their direction and length in the routing algorithm and removing the influence of the coupling coefficient on the gradient propagation, so that the network can work when stacked in multiple layers. Then, the iterative process of routing is simplified to reduce the amount of computation and we introduce the gradient coefficient $lambda$. Further, we tested the performance of our proposed adaptive routing algorithm on CIFAR10, Fashion-MNIST, SVHN and MNIST, while achieving better results than the dynamic routing algorithm.

Max-Min Fair Sensor Scheduling: Game-theoretic Perspective and Algorithmic Solution

We consider the design of a fair sensor schedule for a number of sensors monitoring different linear time-invariant processes. The largest average remote estimation error among all processes is to be minimized. We first consider a general setup for the max-min fair allocation problem. By reformulating the problem as its equivalent form, we transform the fair resource allocation problem into a zero-sum game between a judge and a resource allocator. We propose an equilibrium seeking procedure and show that there exists a unique Nash equilibrium in pure strategy for this game. We then apply the result to the sensor scheduling problem and show that the max-min fair sensor scheduling policy can be achieved.