The adversarial patch is a practical and effective method that modifies a small region on an image, making DNNs fail to classify. Existing empirical defenses against adversarial patch attacks lack theoretical analysis...
详细信息
The adversarial patch is a practical and effective method that modifies a small region on an image, making DNNs fail to classify. Existing empirical defenses against adversarial patch attacks lack theoretical analysis and are vulnerable to adaptive attacks. To overcome such shortcomings, certified defenses that provide a guaranteed classification performance in the face of strong unknown adversarial attacks are proposed. However, on the one hand, existing certified defenses either have low clean accuracy or need specified architecture, which is not robust enough. On the other hand, they can only provide provable accuracy but ignore the relationship to the number of perturbations. In this paper, we propose a certified defense against patch attacks that provides both the provable radius and high classification accuracy. By adding Gaussian noises only on the patch region with a mask, we prove that a stronger certificate with high confidence can be achieved by randomized smoothing. Furthermore, we design a practical scheme based on joint voting to find the patch with a high probability and certify it effectively. Our defense achieves 86.4%clean accuracy and 71.8% certified accuracy on CIFAR-10 exceeding the maximum 60% certified accuracy of existing methods. The clean accuracy of 67.8% and the certified accuracy of 53.6% on ImageNet are better than the state-of-the-art method, whose certified accuracy is 26%.
To address the privacy concerns that arise from centralizing model training on a large number of IoT devices, a revolutionary new distributed learning framework called federated learning has been developed. This setup...
详细信息
Multi-View Stereo (MVS) is a long-standing and fundamental task in computer vision, which aims to reconstruct the 3D geometry of a scene from a set of overlapping images. With known camera parameters, MVS matches pixe...
详细信息
Dynamic graph neural networks(DGNNs)have demonstrated their extraordinary value in many practical ***,the vulnerability of DNNs is a serious hidden danger as a small disturbance added to the model can markedly reduce ...
详细信息
Dynamic graph neural networks(DGNNs)have demonstrated their extraordinary value in many practical ***,the vulnerability of DNNs is a serious hidden danger as a small disturbance added to the model can markedly reduce its *** the same time,current adversarial attack schemes are implemented on static graphs,and the variability of attack models prevents these schemes from transferring to dynamic *** this paper,we use the diffused attack of node injection to attack the DGNNs,and first propose the node injection attack based on structural fragility against DGNNs,named Structural Fragility-based Dynamic Graph Node Injection Attack(SFIA).SFIA firstly determines the target time based on the period ***,it introduces a structural fragile edge selection strategy to establish the target nodes set and link them with the malicious node using serial ***,an optimization function is designed to generate adversarial features for malicious *** on datasets from four different fields show that SFIA is significantly superior to many comparative *** the graph is injected with 1%of the original total number of nodes through SFIA,the link prediction Recall and MRR of the target DGNN link decrease by 17.4%and 14.3%respectively,and the accuracy of node classification decreases by 8.7%.
Forest fires pose a serious threat to ecological balance, air quality, and the safety of both humans and wildlife. This paper presents an improved model based on You Only Look Once version 5 (YOLOv5), named YOLO Light...
详细信息
Forest fires pose a serious threat to ecological balance, air quality, and the safety of both humans and wildlife. This paper presents an improved model based on You Only Look Once version 5 (YOLOv5), named YOLO Lightweight Fire Detector (YOLO-LFD), to address the limitations of traditional sensor-based fire detection methods in terms of real-time performance and accuracy. The proposed model is designed to enhance inference speed while maintaining high detection accuracy on resource-constrained devices such as drones and embedded systems. Firstly, we introduce Depthwise Separable Convolutions (DSConv) to reduce the complexity of the feature extraction network. Secondly, we design and implement the Lightweight Faster Implementation of Cross Stage Partial (CSP) Bottleneck with 2 Convolutions (C2f-Light) and the CSP Structure with 3 Compact Inverted Blocks (C3CIB) modules to replace the traditional C3 modules. This optimization enhances deep feature extraction and semantic information processing, thereby significantly increasing inference speed. To enhance the detection capability for small fires, the model employs a Normalized Wasserstein Distance (NWD) loss function, which effectively reduces the missed detection rate and improves the accuracy of detecting small fire sources. Experimental results demonstrate that compared to the baseline YOLOv5s model, the YOLO-LFD model not only increases inference speed by 19.3% but also significantly improves the detection accuracy for small fire targets, with only a 1.6% reduction in overall mean average precision (mAP)@0.5. Through these innovative improvements to YOLOv5s, the YOLO-LFD model achieves a balance between speed and accuracy, making it particularly suitable for real-time detection tasks on mobile and embedded devices.
Ensemble object detectors have demonstrated remarkable effectiveness in enhancing prediction accuracy and uncertainty quantification. However, their widespread adoption is hindered by significant computational and sto...
详细信息
Software-Defined Networking (SDN) updates network flexibility by decoupling the data plane from control planes, employing a logically centralized yet physically distributed multi-controller architecture. The optimal p...
详细信息
To solve the problems of large-scale data storage and reliable access control in blockchain-based collaborative business process executions with multiple participants and internet of things (IoT) devices, an innovativ...
详细信息
Hybrid Power-line/Visible-light Communication(HPVC)network has been one of the most promising Cooperative Communication(CC)technologies for constructing Smart Home due to its superior communication reliability and har...
详细信息
Hybrid Power-line/Visible-light Communication(HPVC)network has been one of the most promising Cooperative Communication(CC)technologies for constructing Smart Home due to its superior communication reliability and hardware *** research on HPVC networks focuses on the performance analysis and optimization of the Physical(PHY)layer,where the Power Line Communication(PLC)component only serves as the backbone to provide power to light Emitting Diode(LED)*** designing a Media Access Control(MAC)protocol remains a great challenge because it allows both PLC and Visible Light Communication(VLC)components to operate data transmission,i.e.,to achieve a true HPVC network *** solve this problem,we propose a new HPC network MAC protocol(HPVC MAC)based on Carrier Sense Multiple Access/Collision Avoidance(CSMA/CA)by combining IEEE 802.15.7 and IEEE 1901 ***,we add an Additional Assistance(AA)layer to provide the channel selection strategies for sensor stations,so that they can complete data transmission on the selected channel via the specified CSMA/CA mechanism,*** on this,we give a detailed working principle of the HPVC MAC,followed by the construction of a joint analytical model for mathematicalmathematical validation of the HPVC *** the modeling process,the impacts of PHY layer settings(including channel fading types and additive noise feature),CSMA/CA mechanisms of 802.15.7 and 1901,and practical configurations(such as traffic rate,transit buffer size)are comprehensively taken into ***,we prove the proposed analytical model has the ***,through extensive simulations,we characterize the HPVC MAC performance under different system parameters and verify the correctness of the corresponding analytical model with an average error rate of 4.62%between the simulation and analytical results.
The Internet of Things(loT)has grown rapidly due to artificial intelligence driven edge *** enabling many new functions,edge computing devices expand the vulnerability surface and have become the target of malware ***...
详细信息
The Internet of Things(loT)has grown rapidly due to artificial intelligence driven edge *** enabling many new functions,edge computing devices expand the vulnerability surface and have become the target of malware ***,attackers have used advanced techniques to evade defenses by transforming their malware into functionality-preserving *** systematically analyze such evasion attacks and conduct a large-scale empirical study in this paper to evaluate their impact on *** specifically,we focus on two forms of evasion attacks:obfuscation and adversarial *** the best of our knowledge,this paper is the first to investigate and contrast the two families of evasion attacks *** apply 10 obfuscation attacks and 9 adversarial attacks to 2870 malware *** obtained findings are as follows.(1)Commercial Off-The-Shelf(COTS)malware detectors are vulnerable to evasion attacks.(2)Adversarial attacks affect COTS malware detectors slightly more effectively than obfuscated malware examples.(3)Code similarity detection approaches can be affected by obfuscated examples and are barely affected by adversarial attacks.(4)These attacks can preserve the functionality of original malware examples.
暂无评论