An official website of the United States government
Many developers of biometric systems start with modest samples before general deployment. However, they are interested in how their systems will work with much larger samples. To assist them, we evaluated the effect of gallery size on biometric performance. Identification rates describe the performance of biometric identification, whereas ROC-based measures describe the performance of biometric authentication (verification). Therefore, we examined how increases in gallery size affected identification rates (i.e., Rank-1 Identification Rate, or Rank-1 IR) and ROC-based measures such as equal error rate (EER). We studied these phenomena with synthetic data as well as real data from a face recognition study. It is well known that the Rank-1 IR declines with increasing gallery size, and that the relationship is linear against log(gallery size). We have confirmed this with synthetic and real data. We have shown that this decline can be counteracted with the inclusion of additional information (features) for larger gallery sizes. We have also described the curves which can be used to predict how much additional information would be required to stabilize the Rank-1 IR as a function of gallery size. These equations are also linear in log(gallery size). We have also shown that the entire ROC-curve was not systematically affected by gallery size, and so ROC-based scalar performance metrics such as EER are also stable across gallery size. Unsurprisingly, as additional uncorrelated features are added to the model, EER decreases. We were interested in determining the impact of adding more features on the median, spread and shape of similarity score distributions. We present evidence that these decreases in EER are driven primarily by decreases in the spread of the impostor similarity score distribution.
more »
« less
Robust Performance Metrics for Authentication Systems
Research has produced many types of authentication systems that use machine learning. However, there is no consistent approach for reporting performance metrics and the reported metrics are inadequate. In this work, we show that several of the common metrics used for reporting performance, such as maximum accuracy (ACC), equal error rate (EER) and area under the ROC curve (AUROC), are inherently flawed. These common metrics hide the details of the inherent trade-offs a system must make when implemented. Our findings show that current metrics give no insight into how system performance degrades outside the ideal conditions in which they were designed. We argue that adequate performance reporting must be provided to enable meaningful evaluation and that current, commonly used approaches fail in this regard. We present the unnormalized frequency count of scores (FCS) to demonstrate the mathematical underpinnings that lead to these failures and show how they can be avoided. The FCS can be used to augment the performance reporting to enable comparison across systems in a visual way. When reported with the Receiver Operating Characteristics curve (ROC), these two metrics provide a solution to the limitations of currently reported metrics. Finally, we show how to use the FCS and ROC metrics to evaluate and compare different authentication systems.
more »
« less
- Award ID(s):
- 1750987
- PAR ID:
- 10091768
- Date Published:
- Journal Name:
- Network and Distributed Systems Security (NDSS) Symposium 2019
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract—Signature-based Intrusion Detection Systems (SIDSs) are traditionally used to detect malicious activity in networks. A notable example of such a system is Snort, which compares network traffic against a series of rules that match known exploits. Current SIDS rules are designed to minimize the amount of legitimate traffic flagged incorrectly, reducing the burden on network administrators. However, different use cases than the traditional one–such as researchers studying trends or analyzing modified versions of known exploits–may require SIDSs to be less constrained in their operation. In this paper, we demonstrate that applying modifications to real-world SIDS rules allow for relaxing some constraints and characterizing the performance space of modified rules. We develop an iterative approach for exploring the space of modifications to SIDS rules. By taking the modifications that expand the ROC curve of performance and altering them further, we show how to modify rules in a directed manner. Using traffic collected and identified as benign or malicious from a cloud telescope, we find that the removal of a single component from SIDS rules has the largest impact on the performance space. Effectively modifying SIDS rules to reduce constraints can enable a broader range of detection for various objectives, from increased security to research purposes.more » « less
-
Wearable computing devices have become increasingly popular and while these devices promise to improve our lives, they come with new challenges. One such device is the Google Glass from which data can be stolen easily as the touch gestures can be intercepted from a head-mounted device. This paper focuses on analyzing and combining two behavioral metrics, namely, head movement (captured through glass) and torso movement (captured through smartphone) to build a continuous authentication system that can be used on Google Glass alone or by pairing it with a smartphone. We performed a correlation analysis among the features on these two metrics and found that very little correlation exists between the features extracted from head and torso movements in most scenarios (set of activities). This led us to combine the two metrics to perform authentication. We built an authentication system using these metrics and compared the performance among different scenarios. We got EER less than 6% when authenticating a user using only the head movements in one scenario whereas the EER is less than 5% when authenticating a user using both head and torso movements in general.more » « less
-
Artificial intelligence (AI) systems have begun to be deployed in high-stakes contexts, including autonomous driving and medical diagnosis. In contexts such as these, the consequences of system failures can be devastating. It is therefore vital that researchers and policy-makers have a full understanding of the capabilities and weaknesses of AI systems so that they can make informed decisions about where these systems are safe to use and how they might be improved. Unfortunately, current approaches to AI evaluation make it exceedingly difficult to build such an understanding, for two key reasons. First, aggregate metrics make it hard to predict how a system will perform in a particular situation. Second, the instance-by-instance evaluation results that could be used to unpack these aggregate metrics are rarely made available ( 1 ). Here, we propose a path forward in which results are presented in more nuanced ways and instance-by-instance evaluation results are made publicly available.more » « less
-
Sustainability is crucial for combating climate change and protecting our planet. While there are various systems that can pose a threat to sustainability, data centers are particularly significant due to their substantial energy consumption and environmental impact. Although data centers are becoming increasingly accountable to be sustainable, the current practice of reporting sustainability data is often mired with simple green-washing. To improve this status quo, users as well as regulators need to verify the data on the sustainability impact reported by data center operators. To do so, data centers must have appropriate infrastructures in place that provide the guarantee that the data on sustainability is collected, stored, aggregated, and converted to metrics in a secure, unforgeable, and privacy-preserving manner. Therefore, this paper first introduces the new security challenges related to such infrastructure, how it affects operators and users, and potential solutions and research directions for addressing the challenges for data centers and other industry segments.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/https://dx.doi.org/10.14722/ndss.2019.23351
