Test-time domain adaptation is a challenging task that aims to adapt a pre-trained model to limited, unlabeled target data during inference. Current methods that rely on self-supervision and entropy minimization underperform when the self-supervised learning (SSL) task does not align well with the primary objective. Additionally, minimizing entropy can lead to suboptimal solutions when there is limited diversity within minibatches. This paper introduces a meta-learning minimax framework for test-time training on batch normalization (BN) layers, ensuring that the SSL task aligns with the primary task while addressing minibatch overfitting. We adopt a mixed-BN approach that interpolates current test batch statistics with the statistics from source domains and propose a stochastic domain synthesizing method to improve model generalization and robustness to domain shifts. Extensive experiments demonstrate that our method surpasses state-of-the-art techniques across various domain adaptation and generalization benchmarks, significantly enhancing the pre-trained model’s robustness on unseen domains.

Smartphone-based contactless fingerphoto authentication has become a reliable alternative to traditional contact-based fingerprint biometric systems owing to rapid advances in smartphone camera technology. Despite its convenience, fingerprint authentication through fingerphotos is more vulnerable to presentation attacks, which has motivated recent research efforts towards developing fingerphoto Presentation Attack Detection (PAD) techniques. However, prior PAD approaches utilized supervised learning methods that require labeled training data for both bona fide and attack samples. This can suffer from two key issues, namely (i) generalization—the detection of novel presentation attack instruments (PAIs) unseen in the training data, and (ii) scalability—the collection of a large dataset of attack samples using different PAIs. To address these challenges, we propose a novel unsupervised approach based on a state-of-the-art deep-learning-based diffusion model, the Denoising Diffusion Probabilistic Model (DDPM), which is trained solely on bona fide samples. The proposed approach detects Presentation Attacks (PA) by calculating the reconstruction similarity between the input and output pairs of the DDPM. We present extensive experiments across three PAI datasets to test the accuracy and generalization capability of our approach. The results show that the proposed DDPM-based PAD method achieves significantly better detection error rates on several PAI classes compared to other baseline unsupervised approaches.

Face recognition systems (FRSs) typically store databases of discriminative real-valued template vectors, which are extracted from each enrolled user’s facial image(s). Such template databases must be carefully protected for user privacy—indeed, the dangers of template leakages have been widely reported in the literature. In contrast, the similarity scores between queried images and enrolled users is often unprotected and can be readily queried through typical FRS APIs. Such scores provide a potential avenue of adversarial attack on FRSs, but recently proposed score-based attacks remain largely impractical because they essentially rely on trial-and-error strategies that use an enormous number of adaptive queries (>50K) for face reconstruction.We present the first practical score-based face reconstruction and impersonation attack against three commercial FRS APIs: AWS CompareFaces, FACE++, and KAIROS, as well as five commonly used pre-trained open-source FRSs. Our attack is carried out in the black-box FRS model, where the adversary has no knowledge of the FRS (underlying models, parameters, template databases, etc.), except for the ability to make a limited number of similarity score queries. Notably, the attack is straightforward to implement, requires no trial-and-error guessing, and uses a small number of nonadaptive score queries. We motivate the attack by analyzing the topological meaning of similarity scores and then present our novel method using orthogonal face sets: a precomputed approximate basis set of human-like face images that enables us to get meaningful similarity scores from a small number of non-adaptive queries. Our approach successfully reconstructs human-like impersonation images with >20% (resp. >96%) success rates across three test datasets when directly attacking the AWS CompareFaces API (resp. open-source CosFace FRS) using only 100 queries—up to two orders of magnitude fewer queries than previous approaches. We provide evidence that personally identifiable biometric features are captured in our reconstructions by evaluating our approach in transfer-like attack settings and through other image similarity metrics.

Steganalysis can be characterized as detecting a weak noise signal (hidden information) in textured regions of naturally occurring images. These noise signals are typically not perceptible to human eyes, which renders steganalysis a challenging task. On the other hand, recent breakthroughs in deep learning have seen remarkable progress in many applications, ranging from object recognition and segmentation to image generations. While there were efforts to build deep learning networks to perform steganalysis, the proposed architectures exhibit some limitations and a high tendency to overfit. We propose a hybrid deep learning architecture, namely H-StegoNet, to perform spatial steganalysis in this work. Precisely, by combining two different neural networks inspired by handcrafted features and the U-Net, we design a robust architecture that outperforms the existing approaches. Moreover, the experiments we performed under more realistic assumptions, including encoding with the syndrome trellis codes and assuming no prior knowledge of the payload used, thereby defining a rigorous and standard operation procedure for evaluating any steganalysis algorithm.

Due to the increasing vulnerabilities in cyberspace, security alone is not enough to prevent a breach, but cyber forensics or cyber intelligence is also required to prevent future attacks or to identify the potential attacker. The unobtrusive and covert nature of biometric data collection of keystroke dynamics has a high potential for use in cyber forensics or cyber intelligence. In this paper, we investigate the usefulness of keystroke dynamics to establish the person identity. We propose three schemes for identifying a person when typing on a keyboard. We use various machine learning algorithms in combination with the proposed pairwise user coupling technique and show the performance of each separate technique as well as the performance when combining two or more together. In particular, we show that pairwise user coupling in a bottom-up tree structure scheme gives the best performance, both concerning accuracy and time complexity. The proposed techniques are validated by using keystroke data. However, these techniques could equally well be applied to other pattern identification problems. We have also investigated the optimized feature set for person identification by using keystroke dynamics. Finally, we also examined the performance of the identification system when a user, unlike his normal behaviour, types with only one hand, and we show that performance then is not optimal, as was to be expected.

In this paper, we investigate the performance of a continuous authentication system using fuzzy logic techniques. The system monitors mouse and keystroke dynamics behaviour of a user to determine the genuineness. The objective was to design a system that is capable of detecting an impostor user as fast as possible, while not disturbing the genuine user. For our research we build a new dataset consisting of mouse and keystroke dynamics behavioural data of 52 persons, collected in a real life environment (no control over environment or performed tasks) over a period of 5-7 days.

The advanced technologies and sensors in smartphones has led to showcase their potential as a biometric sensor. In this work, we present the feasibility study and challenges in the path forward for using smartphone as a biometric sensor for iris recognition in visible spectrum. Especially, with a limited shelf-life of smartphones, it is anticipated to have enrolment and verification using different camera. In this work, we propose an improvement to segmentation scheme for contactless iris acquisition by approximating the radius range. The proposed method has resulted in a segmentation accuracy of 81%. We also propose various protocols for real-life verification scenarios using smartphones for visible spectrum iris recognition. Finally, results from an extensive set of experiments are presented to validate the anticipated challenges in using smartphone based iris recognition. Being the first of its kind, this work provides the benchmarking results for the smartphone iris database. The best EER is obtained for iPhone in indoor scenario with an impressive EER of 0.48%.

This paper discusses the complexity measurement of a password in relation to the performance of a keystroke dynamics system. The performance of any biometric system depends on the stability of the biometric data provided by the user. We first present a new way to calculate the complexity related to the typing of a password. This complexity metric is then validated with the keystroke dynamics data collected in an experiment, as well as the user's experience during the experiment. Next, we show that the performance of the keystroke dynamics biometric system will depend on the complexity of the password and in particular that the performance of the system decreases with an increasing complexity. This leads then to the conclusion that random passwords might, although harder to guess by an attacker, might not be the most suitable choice in case of keystroke dynamics.