一种基于图像传感器频域重建的新型对抗性示例检测方法.
Shuaina Huang1,2,3, Zhiyong Zhang1,2,3, Bin Song1,2,3
1Information Engineering College, Henan University of Science and Technology, Luoyang 471023, China.
Sensors (Basel, Switzerland)
|September 14, 2024
概括
本研究介绍了频域重建 (FDR),这是一种新的方法,可以在不改变模型的情况下检测卷积神经网络 (CNN) 中的对立例子. FDR有效地消除了对抗性干扰,增强了关键应用程序的CNN稳定性.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 遥感 遥感 遥感 遥感
背景情况:
- 卷积神经网络 (CNN) 在遥感方面表现出色,但易受对抗性示例的影响,危及安全关键的应用.
- 现有的检测方法通常需要CNN修改,增加成本并可能降低性能.
- 对于敏感领域的可靠人工智能来说,对抗敌对攻击的稳定性至关重要.
研究的目的:
- 为CNN提出一个有效的对抗性示例检测算法,不需要修改模型.
- 为了保持正常例子的高分类准确性,同时检测到对立的例子.
- 为了提高CNN在遥感和其他关键应用中的安全性和可靠性.
主要方法:
- 频域重建 (FDR) 通过将输入数据转换为频域,使用里埃转换来检测对立例子.
- 通过修改特定频率来减轻对抗性干扰,并通过逆里埃变换在空间域中重建图像.
- 梯度掩盖被纳入FDR以改善复杂对抗示例的检测.
主要成果:
- 在三个基准数据集中对五次对抗性攻击进行了广泛的实验,证明了FDR在最先进的方法中表现优越.
- 在没有修改底层的CNN架构的情况下,FDR成功地检测了对立的例子.
- 该方法显示了将其集成到传感器件中的潜力,以确保检测安全.
结论:
- 频域重建 (FDR) 提供了一种非侵入性和有效的解决方案,用于检测CNN中的对抗性示例.
- 联邦调查局 (FDR) 提高了CNN对抗敌对攻击的稳定性,而不会影响合法数据的性能.
- 拟议的方法是部署安全可靠的人工智能在安全关键的遥感任务的重大进展.
相关概念视频
01:18Aliasing
124
Accurate signal sampling and reconstruction are crucial in various signal-processing applications. A time-domain signal's spectrum can be revealed using its Fourier transform. When this signal is sampled at a specific frequency, it results in multiple scaled replicas of the original spectrum in the frequency domain. The spacing of these replicas is determined by the sampling frequency.
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
124
01:10Reconstruction of Signal using Interpolation
179
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
179
01:15Discrete Fourier Transform
228
The Discrete Fourier Transform (DFT) is a fundamental tool in signal processing, extending the discrete-time Fourier transform by evaluating discrete signals at uniformly spaced frequency intervals. This transformation converts a finite sequence of time-domain samples into frequency components, each representing complex sinusoids ordered by frequency. The DFT translates these sequences into the frequency domain, effectively indicating the magnitude and phase of each frequency component present...
228
01:03IR Frequency Region: Fingerprint Region
798
IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...
798
01:15Sampling Theorem
310
In signal processing, the analysis of continuous-time signals, denoted as x(t), often involves sampling techniques to convert these signals into discrete-time signals. This process is essential for digital representation and manipulation. A critical component in sampling is the train of impulses, characterized by the sampling interval and the sampling frequency. The relationship between these parameters and the original signal's properties dictates the success of the sampling process.
310
01:25IR Spectrometers
1.1K
There are two main infrared (IR) spectrophotometers: dispersive IR spectrometers and Fourier transform infrared (FTIR) spectrometers. In a dispersive IR spectrometer, a beam of infrared radiation produced by a hot wire is divided into two parallel equal-intensity beams using mirrors. One beam passes through the sample, while another is a reference beam. The beams then move through the monochromator, which separates the radiations into a continuous spectrum of different frequencies. The...
1.1K