图像检索系统在数据扭曲流下保证的稳定性
Hyerin Chung1, Nakyung Lee1, Hansol Lee1
1AI Research, CJ OliveNetworks, Seoul, Korea.
PloS one
|September 28, 2023
概括
敌对攻击威胁到图像搜索系统. 拟议的GuarD框架使用图像质量评估来防御扭曲,提高排名稳定性而不会影响检索准确性.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 信息检索 信息检索
背景情况:
- 图像搜索系统面临来自对抗性攻击和数据干扰的威胁,损害了查询完整性和排名.
- 现有的研究重点是攻击方法,对有效的防御机制进行有限的探索,以抵御此类入侵.
研究的目的:
- 引入GuaRD,这是一个端到端的框架,旨在增强图像检索系统的稳定性,防止对抗性攻击和数据扭曲.
- 整合图像质量评估作为防御策略,平衡检索准确性与防御能力.
主要方法:
- 在图像检索框架内,GuaRD使用图像质量评估 (IQA) 度量作为加权规范化术语.
- 该框架将原始图像赋予更高的等级,并将扭曲的图像赋予更低的等级,以确保可靠和强大的排名.
- 在Waterloo和PieAPP IQA基准上进行了实验,以评估性能和普遍性.
主要成果:
- GuaRD显著提高了性能,增加了原始图像预测的平均互惠排名 (mRR) 61%,并将扭曲查询的预测降低了18%.
- 对平均平均精度 (mAP) 的分析显示了最小的性能偏差,在应用GuaRD后略有下降0.9%,证实了精度的保存.
- 该框架在不同IQA基准中表现出有效性,突出了其通用性.
结论:
- 图像检索系统的GuaRD是一种新且强大的防御机制,用于防止数据扭曲和对抗性操纵.
- 该框架通过整合质量评估来有效提高系统的可靠性和稳定性,而不会显著影响检索准确性.
- 拟议的方法在面对不断变化的安全威胁时,为保护图像搜索系统提供了一个有希望的方向.
相关概念视频
01:19Survival Tree
105
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...
105
01:10Propagation of Uncertainty from Systematic Error
551
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...
551
00:59Propagation of Uncertainty from Random Error
722
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...
722
03:37Uncertainty in Measurement: Accuracy and Precision
73.9K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
73.9K
01:04Random Error
922
Random or indeterminate errors originate from various uncontrollable variables, such as variations in environmental conditions, instrument imperfections, or the inherent variability of the phenomena being measured. Usually, these errors cannot be predicted, estimated, or characterized because their direction and magnitude often vary in magnitude and direction even during consecutive measurements. As a result, they are difficult to eliminate. However, the aggregate effect of these errors can be...
922