Unmanned aerial vehicles (UAVs) are becoming a common solution to urban mobility, and traffic monitoring as well, owing to their ability to be deployed flexibly, ability to see a broader area and real-time sensing. However, the reliability of UAV-assisted traffic systems can be compromised through identity spoofing, Sybil attacks, false data injection, and trajectory manipulation. Current authentication techniques primarily verify cryptographic identities but often cannot detect when a claimed identity is inconsistent with physical movement patterns and settings. To overcome this drawback, this paper presents a context-aware identity validation system, CIV-UAV, for UAV-based urban traffic surveillance. The paradigm combines a model of cryptographic validation, model mobility, on-the-fly visual, road-network, temporal continuity, anomaly scoring, and multi-UAV consensus into a cohesive trust-based validation model. The risk-adaptive policy also adjusts the validation strictness based on the seriousness of the situation and the level of uncertainty. The outcomes of simulations indicate that CIV-UAV enhances identity validation, lowers the false detection and false acceptance rates, and reinforces the detection of spoofing, Sybil behaviour, path forgery, injection of fake events, and vision-communication mismatch attacks. The suggested architecture provides an identity validation system that is easy to implement and can be upgraded to a next-generation UAV-intelligent transportation network.

Unmanned aerial vehicles (UAVs) are also increasingly becoming more often in the transportation infrastructure of smart cities, so that they can successfully achieve real-time observation of traffic, emergency coordination, and two-way communication relaying. However, the security and privacy risks arising in open, highly mobile intelligent transportation systems (ITS) enabled by UAVs are critical, as they pose threats of impersonation, replay, Sybil, and tracking attacks. Secondly, standard static authentication mechanisms are unable to support dynamic risk environments and excessive resource consumption on UAV platforms with limited capacity. To address these challenges, this study introduces a Generative-AI-assisted Risk-Adaptive Authentication (GRAA) system that modulates the intensity of the authentication process based on risk levels identified by mobility, contextual awareness, and the environment. The framework contains unlinkable pseudonymous credentials and, unlike the accumulator-based revocation scheme and AI-based trust evaluation, it is impossible to correlate sessions. The coherence with the majority of attacks is demonstrated under the formal analysis model, which is also based on the real-or-random (ROR) session key, alongside the justifications of forward secrecy and unlinkability. The performance analysis shows that GRAA can achieve up to 87.9% reduction in computation cost and 56.7% reduction in communication overhead compared to pairing-and-group signature schemes, while lowering the latency and energy consumption of the UAVs in a congested urban setting. Generally, the suggested architecture provides a scalable, convenient, and privacy-friendly authentication system for next-generation smart transportation systems that use UAVs.

Recent advancements in AI-synthesized speech have resulted in highly realistic deepfake audio, posing severe threats to authentication systems and digital media trust. Existing detection models struggle to generalize across diverse synthesis methods, especially those involving neural codec-based Audio Language Models (ALMs). In this work, we propose UniTector++, a novel prosody-aware, multi-stream detection architecture that generalizes across vocoder- and codec-based synthesis. UniTector++ incorporates three complementary streams—Whisper-based semantic embeddings, high-level prosodic features, and codec artifact representations—fused through a Multi-Domain Adaptive Graph Attention Fusion (MAGAF) module. Furthermore, an Emotion-Consistency Verification Module (ECVM) reinforces alignment between speech style and prosodic content, and a Universal Adversarial Robustness (UAR) head improves resistance against adversarial attacks. Evaluated on three benchmark datasets—ASVspoof2021, PolyFake, and Codecfake—UniTector++ achieves state-of-the-art performance with average Equal Error Rate (EER) of 0.57% under unseen synthesis scenarios, outperforming competitive baselines by a relative margin of 28%. Our results demonstrate the model’s superior generalization, interpretability, and robustness, offering a significant advancement in universal deepfake speech detection.

Human emotions are intricate and difficult to decipher through various modalities. Current methodologies frequently employ inflexible fusion strategies that do not consider the dynamic and context-sensitive characteristics of emotional expressions in both visual and textual mediums. This paper presents SYMPHONIA (Synchronizing Facial and Textual Modalities for Emotion Understanding), an innovative architecture engineered to capture and amalgamate emotional signals from facial expressions and language, attuned to contextual and modality interactions. There are two parts to SYMPHONIA: a Facial Emotion Branch that uses Vision Transformers and facial landmarks, and a Textual Emotion Branch that uses RoBERTa embeddings and graph-based reasoning. A Dual-Branch Dynamic Attention Mechanism and a Hierarchical Adaptive Fusion Module are used to connect these branches. SYMPHONIA beat the best models on four datasets: IEMOCAP, MELD, CMU-MOSI, and CMU-MOSEI. It got 80.9% accuracy and 80.1% F1-score on IEMOCAP, which was better than Dualgats (74.8%) and EmoCLIP (75.3%). SYMPHONIA got 74.2% accuracy and 73.5% F1-score for MELD. It beat its competitors by getting a 0.86 Pearson correlation on MOSI and a 0.83 on MOSEI for predicting sentiment. Cross-dataset tests showed that SYMPHONIA could generalize, with 66.9% accuracy when trained on IEMOCAP and tested on MELD. This was better than all the baselines. These results show that SYMPHONIA is good at recognizing emotions and analyzing sentiment in different situations, which shows that it can adapt and do well in different settings.