K-means++ vs. Behavioral Biometrics: One Loop to Rule Them All

Abstract

Abstract-Behavioral biometrics, a field that studies patterns in an individual's unique behavior, has been researched actively as a means of authentication for decades. Recently, it has even been adopted in many real world scenarios. In this paper, we study keystroke dynamics, the most researched of such behavioral biometrics, from the perspective of an adversary. We designed two adversarial agents with a standard accuracy convenience tradeoff: Targeted K-means++, which is an expensive, but extremely effective adversarial agent, and Indiscriminate K-means++, which is slightly less powerful, but adds no overhead cost to the attacker. With Targeted K-means++ we could compromise the security of 40-70% of users within ten tries. In contrast, with Indiscriminate K-means++, the security of 30-50% of users was compromised. Therefore, we conclude that while keystroke dynamics has potential, it is not ready for security critical applications yet. Future keystroke dynamics research should use such adversaries to benchmark the performance of the detection algorithms, and design better algorithms to foil these. Finally, we show that the K-means++ adversarial agent generalizes well to even other types of behavioral biometrics data by applying it on a dataset of touchscreen swipes.

BioPrivacy: a behavioral biometrics continuous authentication system based on keystroke dynamics and touch gestures

“…As suggested by Stylios et al (2021b), CA systems need to be evaluated under the high effort approaches to see the actual performance of machine learning and deep learning models under the spectrum of today's possible threats. Therefore, our system should be evaluated against the frog-boiling attack (Wang et al , 2012), the algorithmic attack (Serwadda and Phoha, 2013), the mimic attacks (Negi et al , 2018; Meng et al , 2013) and the snoop-forge-replay attack (Rahman et al , 2013). Finally, our system was tested in a sample of 39 individuals, and we plan to evaluate it in a larger sample of users.…”

Development of a Decision Support System for Urban Planning by Using K-means ++ Algorithm

“…To manage expansive datasets, significant exertion has likewise gone into additionally accelerating k-means, most strikingly by utilizing KD-trees or abusing the triangular disparity to abstain from contrasting every data point and every one of the centroids amid the task step. Persistent upgrades and speculations of the fundamental algorithm have guaranteed it's proceeded with pertinence and step by step expanded its adequacy too [14].…”

Masterkey attacks against free-text keystroke dynamics and security implications of demographic factors

“…For example, a masterface [37], [46] is a face image that matches a surprisingly large part of the population, making it an exciting candidate to break a face recognition system. Moreover, this concept is not constrained to the face domain; examples exist for fingerprints [14] and keystrokes [36], [44]. The fact that biometric recognition performance is not uniform among individuals was already demonstrated in 1998 by Doddington [20].…”