Convolutional neural networks (CNNs) have been extensively used in numerous remote sensing image detection tasks owing to their exceptional performance. Nevertheless, CNNs are often vulnerable to adversarial examples, limiting the uses in different safety-critical scenarios. Recently, how to efficiently detect adversarial examples and improve the robustness of CNNs has drawn considerable focus. The existing adversarial example detection methods require modifying CNNs, which not only affects the model performance but also greatly enhances training cost. With the purpose of solving these problems, this study proposes a detection algorithm for adversarial examples that does not need modification of the CNN models and can simultaneously retain the classification accuracy of normal examples. Specifically, we design a method to detect adversarial examples using frequency domain reconstruction. After converting the input adversarial examples into the frequency domain by Fourier transform, the adversarial disturbance from adversarial attacks can be eliminated by modifying the frequency of the example. The inverse Fourier transform is then used to maximize the recovery of the original example. Firstly, we train a CNN to reconstruct input examples. Then, we insert Fourier transform, convolution operation, and inverse Fourier transform into the features of the input examples to automatically filter out adversarial frequencies. We refer to our proposed method as FDR (frequency domain reconstruction), which removes adversarial interference by converting input samples into frequency and reconstructing them back into the spatial domain to restore the image. In addition, we also introduce gradient masking into the proposed FDR method to enhance the detection accuracy of the model for complex adversarial examples. We conduct extensive experiments on five mainstream adversarial attacks on three benchmark datasets, and the experimental results show that FDR can outperform state-of-the-art solutions in detecting adversarial examples. Additionally, FDR does not require any modifications to the detector and can be integrated with other adversarial example detection methods to be installed in sensing devices to ensure detection safety.
As an auto-parallelization technique with the level of thread on multi-core, Thread-Level Speculation (TLS) which is also called Speculative Multithreading (SpMT), partitions programs into multiple threads and speculatively executes them under conditions of ambiguous data and control dependence. Thread partitioning approach plays a key role to the performance enhancement in TLS. The existing heuristic rules-based approach (HR-based approach) which is an one-size-fits-all strategy, can not guarantee to achieve the satisfied thread partitioning. In this paper, an importancedegree basedthreadpartitioningapproach (IDaTPA) is proposed to realize the partition of irregular programs into multithreads. IDaTPA implements biasing partitioning for every procedure with a machine learning method. It mainly includes: constructing sample set, expression of knowledge, calculation of similarity, prediction model and the partition of the irregular programs is performed by the prediction model. Using IDaTPA, the subprocedures in unseen irregular programs can obtain their satisfied partition. On a generic SpMT processor (called Prophet) to perform the performance evaluation for multithreaded programs, the IDaTPA is evaluated and averagely delivers a speedup of 1.80 upon a 4-core processor. Furthermore, in order to obtain the portability evaluation of IDaTPA, we port IDaTPA to 8-core processor and obtain a speedup of 2.82 on average. Experiment results show that IDaTPA obtains a significant speedup increasement and Olden benchmarks respectively deliver a 5.75% performance improvement on 4-core and a 6.32% performance improvement on 8-core, and SPEC2020 benchmarks obtain a 38.20% performance improvement than the conventional HR-based approach.
As an auto-parallelization technique with the level of thread on multi-core,Thread-Level Speculation (TLS) which is also called Speculative Multithreading(SpMT), partitions programs into multiple threads and speculatively executesthem under conditions of ambiguous data and control dependence. Thread par-titioning approach plays a key role to the performance enhancement in TLS.The existing heuristic rules-based approach (HR-based approach) which is anone-size-fits-all strategy, can not guarantee to achieve the optimal thread parti-tioning. In this paper, an importance degree based thread partitioning approach(IDaTPA) is proposed to realize the partition of irregular programs into mul-tithreads. IDaTPA implements biasing partitioning for every procedure with amachine learning method. It mainly includes: constructing sample set, expres-sion of knowledge, calculation of similarity, prediction model and the partitionof the irregular programs is performed by the prediction model. Using IDaTPA,the subprocedures in unseen irregular programs can obtain their optimal parti-tion. On a generic SpMT processor (called Prophet) to perform the performanceevaluation for multithreaded programs, the IDaTPA is evaluated and averagelydelivers a speedup of 1.80 upon a 4-core processor. Furthermore, in order toobtain the portability evaluation of IDaTPA, we port IDaTPA to 8-core processorand obtain a speedup of 2.82 on average. Experiment results show that IDaTPAobtains a significant speedup increasement and Olden benchmarks respectively deliver a 5.75% performance improvement on 4-core and a 6.32% performanceimprovement on 8-core, and SPEC2020 benchmarks obtain a 38.20% performanceimprovement than the conventional HR-based approach.