通过先前指导知识改善快速对手训练
概括
快速对抗训练 (FAT) 打击白盒攻击,但过度匹配. 我们的方法利用先前的知识来改进对立的例子,防止过度装配,没有额外的训练时间来提高强度.
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:
- 快速对抗训练 (FAT) 增强了对抗白盒攻击的模型稳定性,但容易发生灾难性的过拟合.
- 现有的FAT变体以减轻过度装配往往会导致大量的训练时间处罚.
研究的目的:
- 调查在FAT中对抗性示例质量和灾难性过拟合之间的联系.
- 提出一种新的方法来防止过度装配,并提高对手的稳定性,而不会增加训练时间.
主要方法:
- 比较标准对抗训练和FAT,以了解超拟合动态.
- 开发了使用历史高质量扰动的积极先导向对抗初始化.
- 引入了损失函数平滑性的预先引导规范化和预先引导的整体FAT方法.
主要成果:
- 确定灾难性过度装配与下降的对抗性实例攻击成功率相关.
- 拟议的FGSM-PGK方法通过提高对抗示例质量,有效地防止过拟合.
- 与现有方法相比,在四个数据集上表现出优越的对抗性稳定性.
结论:
- 预先的知识,特别是高质量的对抗性扰动和模型重量,可以防止FAT过拟合.
- 拟议的FGSM-PGK方法为改善白盒场景中的对抗性稳定性提供了一个有效的解决方案.
更多相关视频
05:12Using Virtual Reality to Transfer Motor Skill Knowledge from One Hand to Another
Published on: September 18, 2017
545.9K
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
2.7K
相关概念视频
Improving Translational Accuracy
10.3K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
10.3K
Associative Learning
353
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...
353
Generalization, Discrimination, and Extinction
548
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...
548
Hindsight Biases
3.4K
Hindsight bias leads you to believe that the event you just experienced was predictable, even though it really wasn’t. In other words, you knew all along that things would turn out the way they did. Can you relate this to the phrase "Hindsight is 20/20" now?
3.4K
Purposive Learning
119
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
119
Heuristics
90
Heuristics are problem-solving strategies that use mental shortcuts to simplify decision-making. Unlike algorithms, which must be followed precisely to achieve a correct result, heuristics offer a general problem-solving framework. They save time and energy but can sometimes lead to less rational decisions.
People often rely on heuristics when faced with an overload of information, limited time, low importance of the decision, limited information, or when a heuristic readily comes to mind. For...
People often rely on heuristics when faced with an overload of information, limited time, low importance of the decision, limited information, or when a heuristic readily comes to mind. For...
90
