A Security Enhancement of the Precision Time Protocol Using a Trusted Supervisor Node.

The Precision Time Protocol (PTP) as described in IEEE 1588-2019 provides a sophisticated mechanism to achieve microsecond or even sub-microsecond synchronization of computer clocks in a well-designed and managed network, therefore meeting the needs of even the most time-sensitive industrial and financial applications. However, PTP is prone to many security threats that impact on a correct clock synchronization, leading to potentially devastating consequences. Here, the most vicious attacks are internal attacks, where a threat actor has full access to the infrastructure including any cryptographic keys used. This paper builds on existing research on the impact of internal attack strategies on PTP networks. It shows limitations of existing security approaches to tackle internal attacks and proposes a new security approach using a trusted supervisor node (TSN), in line with prong D as specified in IEEE 1588-2019. A TSN collects and analyzes delay and offset outputs of monitored slaves, as well as timestamps embedded in PTP synchronization messages, allowing it to detect abnormal patterns that point to an attack. The paper distinguishes between two types of TSN with different capabilities and proposes two different detection algorithms. Experiments show the ability of the proposed method to detect all internal PTP attacks, while outlining its limitations.

C3I-SynFace: A synthetic head pose and facial depth dataset using seed virtual human models.

This article presents C3I-SynFace: a large-scale synthetic human face dataset with corresponding ground truth annotations of head pose and face depth generated using the iClone 7 Character Creator "Realistic Human 100" toolkit with variations in ethnicity, gender, race, age, and clothing. The data is generated from 15 female and 15 male synthetic 3D human models extracted from iClone software in FBX format. Five facial expressions - neutral, angry, sad, happy, and scared are added to the face models to add further variations. With the help of these models, an open-source data generation pipeline in Python is proposed to import these models into the 3D computer graphics tool Blender and render the facial images along with the ground truth annotations of head pose and face depth in raw format. The datasets contain more than 100k ground truth samples with their annotations. With the help of virtual human models, the proposed framework can generate extensive synthetic facial datasets (e.g., head pose or face depths datasets) with a high degree of control over facial and environmental variations such as pose, illumination, and background. Such large datasets can be used for the improved and targeted training of deep neural networks.

3D face-model reconstruction from a single image: A feature aggregation approach using hierarchical transformer with weak supervision.

Convolutional Neural Networks (CNN) have gained popularity as the de-facto model for any computer vision task. However, CNN have drawbacks, i.e. they fail to extract long-range perceptions in images. Due to their ability to capture long-range dependencies, transformer networks are adopted in computer vision applications, where they show state-of-the-art (SOTA) results in popular tasks like image classification, instance segmentation, and object detection. Although they gained ample attention, transformers have not been applied to 3D face reconstruction tasks. In this work, we propose a novel hierarchical transformer model, added to a feature pyramid aggregation structure, to extract the 3D face parameters from a single 2D image. More specifically, we use pre-trained Swin Transformer backbone networks in a hierarchical manner and add the feature fusion module to aggregate the features in multiple stages. We use a semi-supervised training approach and train our model in a supervised way with the 3DMM parameters from a publicly available dataset and unsupervised training with a differential renderer on other parameters like facial keypoints and facial features. We also train our network on a hybrid unsupervised loss and compare the results with other SOTA approaches. When evaluated across two public datasets on face reconstruction and dense 3D face alignment tasks, our method can achieve comparable results to the current SOTA performance and in some instances do better than the SOTA methods. A detailed subjective evaluation also shows that our method performs better than the previous works in realism and occlusion resistance.