Physics-informed neural networks (PINNs) have emerged as promising surrogate modes for solving partial differential equations (PDEs). Their effectiveness lies in the ability to capture solution-related features throug...
详细信息
Partial differential equations (PDEs) are an essential computational kernel in physics and engineering. With the advance of deep learning, physics-informed neural networks (PINNs), as a mesh-free method, have shown gr...
详细信息
Adversarial attacks reveal the inherent vulnerability of deep neural networks, which face serious security issues for their security. Among them, the attack against the Deep Neural Network (DNN) application used in th...
Adversarial attacks reveal the inherent vulnerability of deep neural networks, which face serious security issues for their security. Among them, the attack against the Deep Neural Network (DNN) application used in the Industrial Internet of Things (IIoT) is a key area in adversarial attacks. Adversarial examples generated by attackers by adding human-undetectable interference to legitimate examples may cause models to make wrong decision results, resulting in serious accidents. Many detection technologies have been proposed to mitigate the harm of adversarial examples to neural networks, among which the methods based on the difference of feature attribution between normal examples and adversarial examples show state-of-the-art detection performance, but they suffer from detection efficiency. In this work, we focus on improving the detection efficiency of the feature-attribution-based detection methods. We observe that there is still a significant difference in the feature attribution distribution of a normal image and an adversarial image even only some pixels in the image are processed, which can be verified by utilizing the Kolmogorov-Smirnov test. Based on this observation, we first adopt a variety of strategies to sample partial pixels in an image and then utilize the selected pixels to train a feature-attribution-based detector for detecting adversarial examples. Extensive experiments conducted on four datasets (MNIST, CIFAR-10, SVHN, CIFAR-100) against various attacks proved that the detection efficiency of the accelerated detection method is improved (for example, the average execution time was increased by 8.7 times on CIFAR-10) while the detection performance maintains state-of-the-art.
Mesh smoothing methods can enhance mesh quality by eliminating distorted elements, leading to improved convergence in simulations. To balance the efficiency and robustness of traditional mesh smoothing process, previo...
详细信息
Convolutional neural networks (CNN) is playing an important role in many fields. Many applications are able to run the inference process of CNN with pre-trained models on mobile devices in these days. Improving perfor...
详细信息
Training activations of deep neural networks occupy plenty of GPU memory, especially for large-scale deep neuralnetworks. However, the further development of deep neural networks is hampered by the limited GPU memory ...
详细信息
Training activations of deep neural networks occupy plenty of GPU memory, especially for large-scale deep neuralnetworks. However, the further development of deep neural networks is hampered by the limited GPU memory resource. Therefore, the optimal utilization of GPU memory resources is highly demanded. Swapping and recomputation are commonly applied to make better use of GPU memory in deep learning. As an emerging domain, several dilemmas remain: 1) The efficiency of recomputation is limited and swapping between GPU and CPU costs severe time delay;2) There still lacks a dynamic runtime memory manager of tensor swapping and tensor recomputation nowadays;3) Manually decisions for activations of training deep neural network require professional priors and experience. To remedy the above issues, we propose a novel memory manager named DELTA (Dynamic tEnsor offLoading and recompuTAtion). To the best of our knowledge, we are the first to propose a reasonable dynamic runtime manager on the combination of tensor swapping and tensor recomputation without user oversight. In DELTA, we firstly propose a filter algorithm to select the optimal tensors to be released out of GPU memory and secondly present a director algorithm to select a proper action for each of these tensors. Furthermore, prefetching and overlapping are deliberately considered to overcome the time cost caused by swapping and recomputing tensors. Experimental results show that DELTA not only saves 40%-70% of GPU memory, surpassing the state-of-the-art method to a great extent, but also gets comparable convergence results as the baseline with acceptable time delay. Also, DELTA gains 2.04× maximum batchsize when training ResNet-50 and 2.25× when training ResNet-101 compared with the baseline. Besides, comparisons between the swapping cost and recomputation cost in our experiments demonstrate the importance of making a reasonable decision on tensor swapping and tensor recomputation, which refutes the arguments in
In CFD, mesh smoothing methods are commonly utilized to refine the mesh quality to achieve high-precision numerical simulations. Specifically, optimization-based smoothing is used for high-quality mesh smoothing, but ...
详细信息
The human can easily recognize the incongruous parts of an image, for example, perturbations unrelated to the image itself, but are poor at spotting the small geometric transformations. However, in terms of the robust...
详细信息
The human can easily recognize the incongruous parts of an image, for example, perturbations unrelated to the image itself, but are poor at spotting the small geometric transformations. However, in terms of the robustness of deep neural networks (DNNs), the ability to properly recognize objects with small geometric transformations is still a challenge. In this work, we investigate the problem from the perspective of adversarial attacks: does the performance of DNNs degrade even when small geometric transformations are applied to images? To this end, we propose a novel adversarial attack method, called WBA, a Warping-Based Adversarial attack method, which does not introduce information independent of the original images but manipulates the existing pixels of the images by elastic warping transformations to generate adversarial examples that are imperceptible to the human eye. At the same time, existing adversarial attacks typically generate adversarial examples by modifying pixels in the spatial domain of the image, the addition of such perturbations introduces extra information unrelated to the image itself and is easily detected by the naked eyes. We demonstrate the effectiveness of WBA by extensive experiments on commonly used datasets, including MNIST, CIFAR10, and ImageNet. The results show that WBA can quickly generate adversarial examples with the highest adversarial strength, consumes less time, and can be comparable to optimization-based adversarial attack methods in image perception evaluation metrics such as LPIPS, SSIM, and far more than gradient direction-based iterative methods.
With the rapid development of Internet technology, various network attack methods come out one after the other. SQL injection has become one of the most severe threats to Web applications and seriously threatens vario...
详细信息
With the rapid growth of large language models, cloud computing has become an indispensable component of the AI industry. Cloud service providers(CSPs) are establishing AI data centers to service AI workloads. In the ...
详细信息
ISBN:
(数字)9798350387339
ISBN:
(纸本)9798350387346
With the rapid growth of large language models, cloud computing has become an indispensable component of the AI industry. Cloud service providers(CSPs) are establishing AI data centers to service AI workloads. In the face of this surging need for AI computing power, building a connected computing environment across various clouds and forming a JointCloud presents an attractive solution. However, scheduling AI tasks across multiple AI data centers within a JointCloud environment presents a significant challenge: how to balance users’ demands while ensuring CSPs’ fairness in scheduling. Existing research primarily focuses on optimizing scheduling quality with limited consideration for fairness. Therefore, this paper proposes a Fairness-Aware AI-Workloads Allocation method (F3A), a fair cross-cloud allocation technique for AI tasks. F3A utilizes Point and Token to reflect both the resource status and historical task allocations of AI data centers, enabling the consideration of users’ multidimensional demands and facilitating fair task allocation across multiple centers. In order to better assess the fairness of scheduling, we also devised a fairness indicator(FI), based on the Gini coefficient to measure the fairness of task allocation. The experimental results demonstrate that F3A consistently maintains FI within 0.1 across various cluster sizes and different task quantities, representing an improvement of 76.45% compared to classical fair scheduling algorithms round-robin. F3A exhibits commendable performance in ensuring fairness in task allocation while also demonstrating effectiveness in cost reduction and enhancing user satisfaction.
暂无评论