防御和生成对抗性示例与生成的对抗性网络一起
Ying Wang1, Xiao Liao2, Wei Cui2
1State Grid Information and Telecommunication Group Co., Ltd, Beijing, China. yingwang0926@foxmail.com.
Scientific reports
|April 15, 2025
概括
深度神经网络容易受到对抗的例子的影响. 拟议的 DG-GAN 框架防御并生成这些例子,增强深度学习安全性并提供一种新的黑子攻击方法.
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) 是广泛使用的,但容易受到对抗的例子.
- 敌对的例子是微妙修改的输入,导致DNN错误分类.
- 现有的防御机制往往需要修改分类器结构或训练程序.
研究的目的:
- 提出一个新的 DG-GAN 框架,以防范和产生对抗性的例子.
- 建立图像和对抗例子之间的双向映射,用于防御和生成.
- 开发一种与任何分类模型兼容的防御方法,而无需进行结构修改.
主要方法:
- 该DG-GAN框架集成了一个生成器,编码器和区分器.
- 双向映射用于关联图像和对立例子.
- 发电机用于防御,编码器用于生成没有梯度信息的对抗性示例.
主要成果:
- DG-GAN有效地防御各种对抗性攻击,优于现有的防御策略.
- 该框架提高了分类模型的稳定性.
- 作为黑子攻击方法,DG-GAN表现出与黑子攻击方法相比较的性能.
结论:
- 该DG-GAN框架提供了一种多功能解决方案,既可以防御,也可以生成对抗性示例.
- 它增强了深度神经网络的安全性,而不改变现有的模型或培训流程.
- 总局-GAN提供了强大的防御和有效的黑盒攻击的双重能力.
更多相关视频
06:20Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training
Published on: December 6, 2024
2.3K
03:14Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
463
相关概念视频
Sequence Networks of Rotating Machines
592
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
592
Associative Learning
2.1K
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...
2.1K
Generalization, Discrimination, and Extinction
2.1K
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...
2.1K
