在整合转移和基于查询的攻击框架中优化潜在变量
IEEE transactions on pattern analysis and machine intelligence
|September 16, 2024
概括
这项研究引入了黑子对抗性攻击的新框架,提高了可转移性并减少了查询需求. 与现有技术相比,拟议的方法在ImageNet上实现了更高的性能.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习安全 机器学习安全
背景情况:
- 黑盒子对抗性攻击面临局限性:基于转移的攻击由于模型架构不匹配而表现不佳,而基于查询的攻击需要广泛的查询和高维优化.
- 现有的方法在对抗性机器学习中努力平衡攻击效率与计算效率和适应性.
研究的目的:
- 为黑盒子对抗性攻击提出一个新的,综合的框架,它结合了基于转移和基于查询的方法的优势.
- 解决当前对抗性攻击方法的可转移性差和高查询要求的局限性.
主要方法:
- 一个两阶段的框架:首先,训练一个使用对抗损失函数输出对抗扰乱的对抗生成器.
- 隐藏变量被引入为生成器输入,以减少优化维度.
- 第二阶段利用潜变量上的粒子群优化来改进成功攻击的扰动,在ImageNet上演示.
主要成果:
- 在攻击性能方面,拟议的框架显著超过了几种最先进的黑子对抗性攻击方法.
- 在ImageNet数据集上的实验验验证了框架的有效性.
- 该框架通过成功扩展到少数像素攻击场景来展示灵活性.
结论:
- 新的综合框架有效地克服了传统的基于转移和基于查询的黑子攻击的局限性.
- 该方法提供了更好的攻击性能和效率,在对抗性机器学习和稳定性测试中具有更广泛的应用潜力.
相关概念视频
Improving Translational Accuracy
9.4K
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...
9.4K
Multi-input and Multi-variable systems
103
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
In the absence...
103
Column Efficiency: Rate Theory
285
The rate theory of chromatography provides quantitative insight into the shapes and widths of elution bands. These bands are based on the random-walk mechanism governing molecular migration within a column. The Gaussian profile of chromatographic bands arises from the cumulative effect of random molecular motions as they progress through the column.
During elution, a solute molecule experiences numerous transitions between stationary and mobile phases, exhibiting irregular residence times in...
During elution, a solute molecule experiences numerous transitions between stationary and mobile phases, exhibiting irregular residence times in...
285
Variability: Analysis
133
Measures of variability are statistical metrics that reveal the dispersion pattern within a dataset. They are pivotal in biostatistics, providing insights into the heterogeneity within health and biological data. Variability signifies the degree to which data points diverge from one another, helping researchers understand the potential range of values and associated uncertainty within the data.
The range is a simple measure of variability, indicating the difference between the highest and...
The range is a simple measure of variability, indicating the difference between the highest and...
133
Maxwell-Boltzmann Distribution: Problem Solving
1.4K
Individual molecules in a gas move in random directions, but a gas containing numerous molecules has a predictable distribution of molecular speeds, which is known as the Maxwell-Boltzmann distribution, f(v).
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
1.4K
Strategies for Assessing and Addressing Confounding
86
Confounding is a critical issue in epidemiological studies, often leading to misleading conclusions about associations between exposures and outcomes. It occurs when the relationship between the exposure and the outcome is mixed with the effects of other factors that influence the outcome. Given that, addressing confounding is of high importance for drawing accurate inferences in research.
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
86


