马普:面具的敌对扰乱促进黑子攻击的可转移性
概括
蒙面对抗性扰乱 (MAP) 增强了对抗性示例在各种AI模型中的可转移性. 这种方法使扰动多样化,防止过度装配,并提高黑子攻击的有效性.
科学领域:
- 人工智能的人工智能
- 计算机视觉 计算机视觉
- 机器学习安全 机器学习安全
背景情况:
- 对抗的例子对于黑子攻击至关重要,可以在没有内部访问的情况下进行模型欺骗.
- 目前的方法在不同的架构中 (如卷积神经网络 (CNN) 和视觉转换器 (ViT)) 难以转移.
- 有限的对抗性扰动多样性导致代用模型过度匹配,阻碍了可转移性.
研究的目的:
- 提出一种新的方法,即掩盖对抗性扰动 (MAP),以提高对抗性示例的可转移性.
- 为应对跨多种模型架构传输攻击的挑战.
- 通过多样化对手的干扰来提高黑子攻击的有效性.
主要方法:
- 引入了掩盖的对抗性扰动 (MAP),以使对抗性扰动多样化.
- 在生成过程中,MAP随机地掩盖了扰动补丁.
- 这迫使剩余的补丁保持攻击有效性,多样化干扰和减轻代用模型过拟合.
主要成果:
- 与现有方法相比,MAP在各种架构中展示了优越的可转移性.
- 这种方法有效地欺骗了卷积和自我注意力机制.
- MAP 始终不断地推动各种黑子攻击,实现了最先进的性能.
结论:
- 有限的扰动多样性是限制对抗性可转移性的关键因素.
- MAP有效地分散了干扰,减轻了过度装配,并提高了跨架构的可转移性.
- 拟议的方法在黑子对抗性攻击方面取得了重大进展.
相关概念视频
Masking and Demasking Agents
2.7K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
2.7K
Propagation of Uncertainty from Random Error
1.1K
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
1.1K
Randomized Experiments
7.3K
The randomization process involves assigning study participants randomly to experimental or control groups based on their probability of being equally assigned. Randomization is meant to eliminate selection bias and balance known and unknown confounding factors so that the control group is similar to the treatment group as much as possible. A computer program and a random number generator can be used to assign participants to groups in a way that minimizes bias.
Simple randomization
Simple...
Simple randomization
Simple...
7.3K
Propagation of Uncertainty from Systematic Error
891
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
891
Generalization, Discrimination, and Extinction
813
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...
813
Improving Translational Accuracy
11.9K
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...
11.9K
