The ever growing realism and quality of generated videos makes it increasingly harder for humans to spot deepfake content, who need to rely more and more on automatic deepfake detectors. However, deepfake detectors are also prone to errors, and their decisions are not explainable, leaving humans vulnerable to deepfake-based fraud and misinformation. To this end, we introduce ExDDV, the first dataset and benchmark for Explainable Deepfake Detection in Video. ExDDV comprises around 5.4K real and deepfake videos that are manually annotated with text descriptions (to explain the artifacts) and clicks (to point out the artifacts). We evaluate a number of vision-language models on ExDDV, performing experiments with various fine-tuning and in-context learning strategies. Our results show that text and click supervision are both required to develop robust explainable models for deepfake videos, which are able to localize and describe the observed artifacts. Our novel dataset and code to reproduce the results are available at https://github.com/vladhondru25/ExDDV.

This paper presents a novel anomaly detection methodology termed Statistical Aggregated Anomaly Detection (SAAD). The SAAD approach integrates advanced statistical techniques with machine learning, and its efficacy is demonstrated through validation on real sensor data from a Hardware-in-the-Loop (HIL) environment within the automotive domain. The key innovation of SAAD lies in its ability to significantly enhance the accuracy and robustness of anomaly detection when combined with Fully Connected Networks (FCNs) augmented by dropout layers. Comprehensive experimental evaluations indicate that the standalone statistical method achieves an accuracy of 72.1%, whereas the deep learning model alone attains an accuracy of 71.5%. In contrast, the aggregated method achieves a superior accuracy of 88.3% and an F1 score of 0.921, thereby outperforming the individual models. These results underscore the effectiveness of SAAD, demonstrating its potential for broad application in various domains, including automotive systems.

In this paper, a deep neural network approach and a neuro-symbolic one are proposed for classification and regression. The neuro-symbolic predictive models based on Logic Tensor Networks are capable of discriminating and in the same time of explaining the characterization of bad connections, called alerts or attacks, and of normal connections. The proposed hybrid systems incorporate both the ability of deep neural networks to improve on their own through experience and the interpretability of the results provided by symbolic artificial intelligence approach. To justify the need for shifting towards hybrid systems, explanation, implementation, and comparison of the dense neural network and the neuro-symbolic network is performed in detail. For the comparison to be relevant, the same datasets were used in training and the metrics resulted have been compared. A review of the resulted metrics shows that while both methods have similar precision in their predictive models, with Logic Tensor Networks being also possible to have interactive accuracy and deductive reasoning over data. Other advantages and disadvantages such as overfitting mitigation and scalability issues are also further discussed.

A hot topic of Artificial Intelligence right now is image generation from prompts. DALL-E 2 is one of the biggest names in this domain, as it allows people to create images from simple text inputs, to even more complicated ones. The company that made this possible, OpenAI, has assured everyone that visited their website that "Our mission is to ensure that artificial general intelligence benefits all humanity". A noble idea in our opinion, that also stood as the motive behind us choosing this subject. This paper analyzes the ethical implications of an AI image generative system, with an emphasis on how society is responding to it, how it probably will and how it should if all the right measures are taken.

In the last decade, damage detection approaches swiftly changed from advanced signal processing methods to machine learning and especially deep learning models, to accurately and non-intrusively estimate the state of the beam structures. But as the deep learning models reached their peak performances, also their limitations in applicability and vulnerabilities were observed. One of the most important reason for the lack of trustworthiness in operational conditions is the absence of intrinsic explainability of the deep learning system, due to the encoding of the knowledge in tensor values and without the inclusion of logical constraints. In this paper, we propose a neuro-symbolic model for the detection of damages in cantilever beams based on a novel cognitive architecture in which we join the processing power of convolutional networks with the interactive control offered by queries realized through the inclusion of real logic directly into the model. The hybrid discriminative model is introduced under the name Logic Convolutional Neural Regressor and it is tested on a dataset of values of the relative natural frequency shifts of cantilever beams derived from an original mathematical relation. While the obtained results preserve all the predictive capabilities of deep learning models, the usage of three distances as predicates for satisfiability, makes the system more trustworthy and scalable for practical applications. Extensive numerical and laboratory experiments were performed, and they all demonstrated the superiority of the hybrid approach, which can open a new path for solving the damage detection problem.