Mirko Casu

The landscape of synthetic media has been irrevocably altered by text-to-video (T2V) models, whose outputs are rapidly approaching indistinguishability from reality. Critically, this technology is no longer confined to large-scale labs; the proliferation of efficient, open-source generators is democratizing the ability to create high-fidelity synthetic content on consumer-grade hardware. This makes existing face-centric and manipulation-based benchmarks obsolete. To address this urgent threat, we introduce SynthForensics, to the best of our knowledge the first human-centric benchmark for detecting purely synthetic video deepfakes. The benchmark comprises 6,815 unique videos from five architecturally distinct, state-of-the-art open-source T2V models. Its construction was underpinned by a meticulous two-stage, human-in-the-loop validation to ensure high semantic and visual quality. Each video is provided in four versions (raw, lossless, light, and heavy compression) to enable real-world robustness testing. Experiments demonstrate that state-of-the-art detectors are both fragile and exhibit limited generalization when evaluated on this new domain: we observe a mean performance drop of 29.19% AUC, with some methods performing worse than random chance, and top models losing over 30 points under heavy compression. The paper further investigates the efficacy of training on SynthForensics as a means to mitigate these observed performance gaps, achieving robust generalization to unseen generators (93.81% AUC), though at the cost of reduced backward compatibility with traditional manipulation-based deepfakes. The complete dataset and all generation metadata, including the specific prompts and inference parameters for every video, will be made publicly available at [link anonymized for review].

Autism Spectrum Disorder (ASD) affects about one child in 36 and stays underdiagnosed, because the assessments that detect it are long and hard to scale. We present a four-phase pipeline that classifies ASD from the gaze recorded on one image, for mobile hardware. A two-stream teacher fuses frozen ViT-B/16 spatial features with a light temporal gaze encoder, then distils into a 1.6M-parameter MobileNetV3 student exported as an ONNX graph inside a prototype Android app. On the Saliency4ASD dataset (28 children), the traditional exact-14-subject subset gives the student an out-of-fold per-image AUC of 0.9894 and accuracy of 0.9346. Ablations trace most of this score to stimulus identity: a held-out stimulus protocol collapses the same student to AUC 0.634. We therefore built a third protocol that neither confound can shortcut, a fixed, class-balanced stimulus set shown to children the model has never seen, matching how the app is actually used. Here the student reaches a per-image AUC of 0.688 and, once a session’s predictions are pooled, a per-subject AUC of 0.959; forty stimuli sustain 0.947 in under three minutes. The work is a case study of multi-stream distillation under constrained data, released open-source for reproducibility and external validation.

Digital and mobile health technologies offer promising solutions for smoking detection and cessation. This scoping review examines the current state of research and development in this field, encompassing smartphone applications, wearable devices, and sensor-based systems. We analyzed 49 studies published between 2019 and 2023 from PubMed and ACM Digital Library, focusing on technology features, outcomes, and evaluation methods. Wearable sensors and smartphone apps show potential in combating smoking addiction and improving quit rates. Motion sensors for hand-to-mouth gesture detection achieve high accuracy in controlled settings but face challenges in real-world applications. Machine learning models and wireless signal detection techniques yield encouraging results but require further refinement. Smartphone apps provide personalized plans and progress tracking, though most rely on manual logging and lack rigorous scientific evaluation. Our findings suggest that digital health technologies could significantly enhance smoking cessation efforts. However, more robust evaluation methods and integration of sensor data with machine learning are needed to improve usability and effectiveness. Continued research and innovation in this field are crucial for developing reliable, practical solutions and integrating these technologies into clinical programs.

Mental health disorders are a leading cause of disability worldwide, and there is a global shortage of mental health professionals. AI chatbots have emerged as a potential solution, offering accessible and scalable mental health interventions. This study aimed to conduct a scoping review to evaluate the effectiveness and feasibility of AI chatbots in treating mental health conditions. A literature search was conducted across multiple databases, including MEDLINE, Scopus, and PsycNet, as well as using AI-powered tools like Microsoft Copilot and Consensus. Relevant studies on AI chatbot interventions for mental health were selected based on predefined inclusion and exclusion criteria. Data extraction and quality assessment were performed independently by multiple reviewers. The search yielded 15 eligible studies covering various application areas, such as mental health support during COVID-19, interventions for specific conditions (e.g., depression, anxiety, substance use disorders), preventive care, health promotion, and usability assessments. AI chatbots demonstrated potential benefits in improving mental and emotional well-being, addressing specific mental health conditions, and facilitating behavior change. However, challenges related to usability, engagement, and integration with existing healthcare systems were identified. AI chatbots hold promise for mental health interventions, but widespread adoption hinges on improving usability, engagement, and integration with healthcare systems. Enhancing personalization and context-specific adaptation is key. Future research should focus on large-scale trials, optimal human–AI integration, and addressing ethical and social implications.

This paper examines the impact of cognitive biases on decision-making in forensics and digital forensics, exploring biases such as confirmation bias, anchoring bias, and hindsight bias. It assesses existing methods to mitigate biases and improve decision-making, introducing the novel “Impostor Bias”, which arises as a systematic tendency to question the authenticity of multimedia content, such as audio, images, and videos, often assuming they are generated by AI tools. This bias goes beyond evaluators’ knowledge levels, as it can lead to erroneous judgments and false accusations, undermining the reliability and credibility of forensic evidence. Impostor Bias stems from an a priori assumption rather than an objective content assessment, and its impact is expected to grow with the increasing realism of AI-generated multimedia products. The paper discusses the potential causes and consequences of Impostor Bias, suggesting strategies for prevention and counteraction. By addressing these topics, this paper aims to provide valuable insights, enhance the objectivity and validity of forensic investigations, and offer recommendations for future research and practical applications to ensure the integrity and reliability of forensic practices.