With its remarkable capability for automated feature extraction, deep neural networks (DNNs) have achieved significant breakthroughs in numerous fields. However, recent studies indicate that deep models are vulnerable to adversarial attacks. In the automatic modulation recognition (AMR) task, the attacker injects imperceptible adversarial perturbations into the radio signals, causing the receiver to misidentify the adversarial examples as incorrect modulation patterns. In this article, we propose an input-independent universal adversarial perturbation (UAP) generation method to attack DNN-based AMR. The proposed method, termed Joint Metric-based Universal Adversarial Perturbation (JM-UAP), strives to enhance the aggressiveness of UAPs by minimizing the similarity metric between feature vectors extracted from benign examples and adversarial examples. To achieve this, feature vectors derived from the penultimate layer of the DNN are chosen as the optimization objects. The dissimilarity between these feature vectors is assessed by combining two metrics, the Adjusted cosine similarity and the Pearson correlation. Extensive experiments demonstrate that our approach significantly reduces the accuracy of AMR models, exhibits robust transferability across various deep models and multiple signal-to-noise ratios (SNRs) datasets, and performs well even in asynchronous scenarios.
Although Deep neural networks (DNN) can achieve higher performance in automatic modulation recognition, they are known to vulnerable to adversarial perturbations, which are strategically added to inputs can fool the DNN model. In this letter, we propose a novel sparse attack scheme based on adversarial generative networks, which enables more covert attacks while preserving communication quality. This new scheme incorporates adversarial training into the discriminator, which not only improves attack performance but also enhances the stability of the training process for adversarial generative networks. Experimental results demonstrate that the proposed scheme outperforms other sparse attack approaches in terms of generation time and transferability.
Unsupervised feature selection (UFS) has been widely used in many machine learning applications, since it can alleviate burdens on the curse of high dimensional data. However, existing works design the UFS methods with the assumption that the complete information of dataset can be observed. In this paper, we propose a UFS method from incomplete data by further introducing ℓ 2,1 -norm minimization. In order to exploit feature relevance for UFS, we show that ℓ 2,1 -norm minimization should be elaborately dealt with unobserved information, which can be finely described with the use of an indicator matrix. The proposed ℓ 2,1 -norm minimization UFS from incomplete data (LUFS) can be directly solved by a convex optimization problem, and we design an alternative algorithm to optimize the convex problem, where the convergence of LUFS algorithm is also proved theoretically and experimentally. Empirical results demonstrate the effectiveness of LUFS with the state-of-the-art methods on real incomplete datasets.
Automatic modulation recognition (AMR) serves as a crucial component in domains such as cognitive radio and electromagnetic countermeasures, acting as a significant prerequisite for the efficient signal processing of receivers. Deep neural networks (DNNs), despite their effectiveness, are known to be vulnerable to adversarial attacks. This vulnerability has inspired the introduction of subtle interference to wireless communication signals—interference so minuscule that it is difficult for the human eye to discern. Such interference can mislead eavesdroppers into erroneous modulation pattern recognition when using DNNs, thereby camouflaging communication signal modulation patterns. Nonetheless, the majority of current camouflage methods used for electromagnetic signal modulation recognition rely on a global perturbation of the signal. They fail to consider the local agility of signal disturbance and the concealment requirements for bait signals that are intercepted by the interceptor. This paper presents a generator framework designed to produce perturbations with sparse properties. Furthermore, we introduce a method to reduce spectral loss, which minimizes the spectral difference between adversarial perturbation and the original signal. This method makes perturbation more challenging to monitor, thereby deceiving enemy electromagnetic signal modulation recognition systems. The experimental results validated that the proposed method significantly outperformed existing methods in terms of generation time. Moreover, it can generate adversarial signals characterized by high deceivability and transferability even under extremely sparse conditions.
10 April 2016 in Mathematical Problems in Engineering
We present a new approach for the analysis of iterative peeling decoding recovery algorithms in the context of Low-Density Parity-Check (LDPC) codes and compressed sensing. The iterative recovery algorithm is particularly interesting for its low measurement cost and low computational complexity. The asymptotic analysis can track the evolution of the fraction of unrecovered signal elements in each iteration, which is similar to the well-known density evolution analysis in the context of LDPC decoding algorithm. Our analysis shows that there exists a threshold on the density factor; if under this threshold, the recovery algorithm is successful; otherwise it will fail. Simulation results are also provided for verifying the agreement between the proposed asymptotic analysis and recovery algorithm. Compared with existing works of peeling decoding algorithm, focusing on the failure probability of the recovery algorithm, our proposed approach gives accurate evolution of performance with different parameters of measurement matrices and is easy to implement. We also show that the peeling decoding algorithm performs better than other schemes based on LDPC codes.
One of the more representative tasks to detect large-scale network behavior data is to use support vector machine (SVM) to extract the characteristics of network data to establish Intrusion detection model. However, the traditional "ℓ 2 -norm" SVM can fit the model to some extent, it is prone to over fitting. In this paper, the sparse support vector machine (S-SVM) algorithm obtained by "ℓ 1 -norm" is used to extract and classify the network behavior data set based on the sparseness of the network behavior data set. Column and constraint generation algorithm is introduced to solve the S-SVM model, and the one-to-one method is used to expand it into a multi-classification sparse support vector machine. Finally, the KDD (knowledge discovery and data mining) CUP 1999 data set was used for experiments. By comparing with the SGD (stochastic gradient descent) and Barrier algorithm, the efficiency and accuracy of this multi-classification S-SVM algorithm in NBAD (network behavior anomaly detection) were verified.
About Me
Weijun Zeng was born in 1986, and his research interests are communication and signal processing and machine learning.
Weijun Zeng was born in 1986, and his research interests are communication and signal processing and machine learning.