The paper introduces Score-Guided Classification (SGC), a novel framework that uses an unsupervised anomaly score as a 'Pathological Prior' to guide EEG-based depression detection, overcoming the limi…

Sympatheia is a speech-to-speech dialogue framework that generates emotionally adaptive responses by conditioning its output on continuous affect signals derived from user speech or external multimoda…

This study compares multiple post-hoc explainable AI methods (e.g., DeepSHAP, GradCAM) to interpret how deep learning models use EEG data to detect Major Depressive Disorder, finding that while method…

The paper proposes a novel, highly secure real-time ECG monitoring framework that uses a patient's own ECG signal characteristics to generate unique, dynamic encryption keys, ensuring confidential dat…

The paper introduces Acoustic Interference Attack (AIA), a novel jailbreak method that bypasses Large Audio Language Model (LALM) safety alignments by manipulating the underlying acoustic latent seman…

This paper provides a unified taxonomy and controlled empirical evaluation of jailbreak attacks and defenses for Large Audio Language Models (LALMs), demonstrating that safety evaluation must consider…

The paper proposes Family-Grouped Hierarchical Federated Learning (Family-FL) combined with a highly optimized Tiny CNN-LSTM model to enable privacy-preserving ECG monitoring on ultra-resource-constra…

The paper proposes Asymmetric Phase Coding (APC), a training-free cryptographic audio watermarking scheme that achieves high extraction rates (97.5%-98.3%) across various real-world and adversarial at…

The paper proposes an end-to-end forensic pipeline using steganographic attribution and multimodal harm detection to reliably trace and attribute harmful misuse of AI-generated imagery on social platf…

This paper provides the first comprehensive review of threats and defenses specifically targeting on-device AI inference, revealing a significant imbalance where certain attack types, like adversarial…

The paper designed a minimalist BCMI system to translate EEG-measured emotional valence into adaptive music, but preliminary testing showed that frontal alpha asymmetry was not reliably modulated by i…

The paper proposes UF-AMA, a unified framework that achieves state-of-the-art cross-domain emotion recognition by adaptively aligning and fusing multimodal physiological signals like EEG and eye-track…

TimeMark proposes a trustworthy time watermarking framework that uses cryptographic techniques and error-correcting codes to achieve 100% accurate recovery of the generation time from AIGC, resisting…

The paper identifies a new class of difficult-to-detect trustworthiness failures, termed 'Silent Failures,' that arise when personalizing foundation models using federated learning, arguing that curre…

STEP introduces a novel, black-box, retraining-free detector that profiles audio samples using dual perturbation branches to detect backdoor attacks by exploiting the characteristic instability of hid…

The paper introduces musicPIIrate, a novel tool that demonstrates how Offensive AI can infer sensitive user attributes (like age, gender, and personality) from public music playlists, and proposes Jam…