通过适应性惯性和振幅频谱脱落来加强对抗性示例的可转移性
Huanhuan Li1, Wenbo Yu1, He Huang1
1School of Electronics and Information Engineering, Soochow University, Suzhou 215006, PR China.
概括
新的方法,即适应性惯性代性快速渐变信号方法 (AdaI2-FGSM) 和振幅频谱脱落方法 (ASDM),产生了高度可转移的对抗性示例. 这些攻击克服了现有方法的局限性,提高了深度神经网络的安全性.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 深度神经网络 (DNN) 容易受到对抗性示例的影响,导致自信的错误预测.
- 现有的对抗性攻击方法往往缺乏可转移性,特别是对抗经过强有力的训练或防御模型.
研究的目的:
- 提出创新的方法来生成高度可转移的对抗性示例.
- 提高对各种深度学习模型的对抗性攻击的有效性.
主要方法:
- 适应性惯性代快梯度信号方法 (AdaI2-FGSM):将适应性惯性集成到梯度式攻击中,以获得更平坦的优化和更好的可转移性.
- 广度频谱丢失方法 (ASDM):采用损失保护的频域转换和丢失不变性来增强替代模型的概括性.
主要成果:
- 与现有的基于梯度的高级攻击相比,AdaI2-FGSM和ASDM显示出更好的可转移性.
- 提出的方法在与ImageNet兼容的数据集上实现了更高的可转移性.
- 整合AdaI2-FGSM和ASDM产生了更强大的对抗性例子.
结论:
- 开发的AdaI2-FGSM和ASDM方法有效地产生了高度可转移的对抗示例.
- 这些技术在对抗性攻击能力方面提供了显著的进步,特别是对抗强大的DNN.
- 拟议的方法通过提供更具挑战性的对抗性示例来增强深度学习模型的安全分析.
相关概念视频
Aliasing
163
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...
163
Difference from Background: Limit of Detection
6.5K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
6.5K
Generalization, Discrimination, and Extinction
632
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
632
Survival Tree
115
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
115
Buffer Effectiveness
49.2K
Buffer solutions do not have an unlimited capacity to keep the pH relatively constant . Instead, the ability of a buffer solution to resist changes in pH relies on the presence of appreciable amounts of its conjugate weak acid-base pair. When enough strong acid or base is added to substantially lower the concentration of either member of the buffer pair, the buffering action within the solution is compromised.
The buffer capacity is the amount of acid or base that can be added to a given volume...
The buffer capacity is the amount of acid or base that can be added to a given volume...
49.2K
Associative Learning
450
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
450


