Studies have shown that deep neural networks(DNNs) are vulnerable to adversarial examples(AEs) that induce incorrect behaviors. To defend these AEs, various detection techniques have been developed. However, most of t...
详细信息
Studies have shown that deep neural networks(DNNs) are vulnerable to adversarial examples(AEs) that induce incorrect behaviors. To defend these AEs, various detection techniques have been developed. However, most of them only appear to be effective against specific AEs and cannot generalize well to different AEs. We propose a new detection method against AEs based on the maximum channel of saliency maps(MCSM). The proposed method can alter the structure of adversarial perturbations and preserve the statistical properties of images at the same time. We conduct a complete evaluation on AEs generated by 6 prominent adversarial attacks on the Image Net large scale visual recognition challenge(ILSVRC) 2012 validation sets. The experimental results show that our method performs well on detecting various AEs.
It can be observed from looking backward that processor architecture is improved through spirally shifting from simple to complex and from complex to simple. Nowadays we are facing another shifting from complex to sim...
详细信息
It can be observed from looking backward that processor architecture is improved through spirally shifting from simple to complex and from complex to simple. Nowadays we are facing another shifting from complex to simple, and new innovative architecture will emerge to utilize the continuously increasing transistor budgets. The growing importance of wire delays, changing workloads, power consumption, and design/verification complexity will drive the forthcoming era of Chip Multiprocessors (CMPs). Furthermore, typical CMP projects both from industries and from academics are investigated. Through going into depths for some primary theoretical and implementation problems of CMPs, the great challenges and opportunities to future CMPs are presented and discussed. Finally, the Godson series microprocessors designed in China are introduced.
Fiber materials are key materials that have changed human history and promoted the progress of human civilization. In ancient times, humans used feathers and animal skins for clothing, and later they widely employed n...
详细信息
Fiber materials are key materials that have changed human history and promoted the progress of human civilization. In ancient times, humans used feathers and animal skins for clothing, and later they widely employed natural fibers such as cotton, hemp, silk and wool to make fabrics(Fig. 1a). Chinese ancestors had mastered the art of natural fiber weaving as early as the Neolithic *** thousand years ago, people were already familiar with and adept at techniques for spinning natural fibers [1].
In this paper, we consider a general and practical complex network model, in which there exist couplings with and without time delays, and the coupled functions among nodes are also nonlinear. For this network model, ...
详细信息
ISBN:
(纸本)9789881563910
In this paper, we consider a general and practical complex network model, in which there exist couplings with and without time delays, and the coupled functions among nodes are also nonlinear. For this network model, we investigate its finite-time synchronization by designing some general static and adaptive controllers respectively. Using the finite-time stability theory, some useful finite-time synchronization criteria are derived. Finally, numerical simulations are given to demonstrate the correctness of our theoretical results.
In this paper, we investigate the synchronization problem for nonlinearly coupled networks under periodically intermittent pinning control, where the coupling matrix denoting network topology is assumed to be symmetri...
详细信息
ISBN:
(纸本)9781467355339
In this paper, we investigate the synchronization problem for nonlinearly coupled networks under periodically intermittent pinning control, where the coupling matrix denoting network topology is assumed to be symmetric. A sufficient condition to guarantee global synchronization is presented. Moreover, a centralized adaptive intermittent control is designed and its validity is rigorously proved. Finally, some numerical examples are presented to demonstrate the correctness of obtained theoretical results.
In this paper,the cluster synchronization problem for nonlinearly coupled networks under periodically intermittent pinning control is *** first,a sufficient condition to guarantee cluster synchronization is ***,an ada...
详细信息
ISBN:
(纸本)9781479900305
In this paper,the cluster synchronization problem for nonlinearly coupled networks under periodically intermittent pinning control is *** first,a sufficient condition to guarantee cluster synchronization is ***,an adaptive intermittent control algorithm is designed to the control strength and its validity is rigorously ***,some numerical examples are presented to demonstrate the correctness of obtained theoretical results.
In this paper, we investigate the cluster synchronization problem with unbounded time-varying delays for complex networks by adding some external controllers. Previous related works mainly focused on bounded time-vary...
详细信息
ISBN:
(纸本)9789881563910
In this paper, we investigate the cluster synchronization problem with unbounded time-varying delays for complex networks by adding some external controllers. Previous related works mainly focused on bounded time-varying or constant time delays, which may not be consistent with the real world. Therefore, unbounded time-varying delays is considered in this paper,which can be regarded as the main difference between this paper and previous related works. We discuss the necessary condition for cluster synchronization with external controllers, which can be used to guide the design of external controllers. Then, by using the Lyapunov function method, we prove that cluster synchronization could be achieved under some sufficient ***, the effects of time delays for the convergence of cluster synchronization are also discussed, which are named as theμ-cluster synchronization. Finally, numerical simulations are presented to show the validity of the obtained criteria.
Time intervals are often associated with tuples to represent their valid time in temporal relations, where overlap join is crucial for various kinds of queries. Many existing overlap join algorithms use indices based ...
详细信息
Time intervals are often associated with tuples to represent their valid time in temporal relations, where overlap join is crucial for various kinds of queries. Many existing overlap join algorithms use indices based on tree structures such as quad-tree, B+-tree and interval tree. These algorithms usually have high CPU cost since deep path traversals are unavoidable, which makes them not so competitive as data-partition or plane-sweep based algorithms. This paper proposes an efficient overlap join algorithm based on a new two-layer flat index named as Overlap Interval Inverted Index (i.e., O2i Index). It uses an array to record the end points of intervals and approximates the nesting structures of intervals via two functions in the first layer, and the second layer uses inverted lists to trace all intervals satisfying the approximated nesting structures. With the help of the new index, the join algorithm only visits the must-be-scanned lists and skips all others. Analyses and experiments on both real and synthetic datasets show that the proposed algorithm is as competitive as the state-of-the-art algorithms.
Accurate weather forecasts are important for disaster prevention, agricultural planning, and water resource management. Traditional numerical weather prediction (NWP) methods offer physically interpretable high-accura...
详细信息
Cloud computing is an emerging paradigm and it has been accepted and researched widely both in industry and academic fields. Instance-intensive workflows are workflows with a great number of concurrent instances;they ...
详细信息
Cloud computing is an emerging paradigm and it has been accepted and researched widely both in industry and academic fields. Instance-intensive workflows are workflows with a great number of concurrent instances;they are typical applications in cloud computing environment. However, cloud resources consist of unreliable servers;it becomes increasingly important to provide reliable scheduling strategy. Considering unreliable cloud resources and QoS requirements of instanceintensive workflows, we propose Trust-drive Minimize Cost Within Deadline (TD-MCWD) scheduling algorithm. On the one hand, the TD-MCWD algorithm staggers deadlines of the large number of concurrent instances of the same nature, expecting to get cheaper and more intensively competitive resources. On the other hand, considering the risk factors on the basis of resource reliability was estimated by trust model, the TD-MCWD algorithm tends to assign the task to the high reliable resource. Simulation experiment shows TD-MCWD algorithm can reduce the rate of delayed instance completion and the average execution cost of successful instance completion. Besides, TD-MCWD has a better load balancing and shows a better performance.
暂无评论