Researchers present a self-supervised method for reconstructing typed text from keystroke sounds without labeled data, achieving high accuracy in various scenarios.

The paper introduces DECKER, a domain-invariant framework that significantly improves cross-keyboard keystroke inference by normalizing device variations and leveraging linguistic context, demonstrati…

This paper introduces a systematic, privacy-preserving method using keystroke dynamics to robustly distinguish between human typing and automated HID injection attacks, independent of user identity.

The paper proposes a diagnostic framework using controlled acoustic perturbations to identify shortcut dependencies in deepfake audio detection models, revealing non-speech intervals as a dominant sho…

The paper introduces Noise-Aware BEATs (NABEATs), a noise-aware audio self-supervised learning framework that estimates clean BEATs representations from noisy audio signals using an auxiliary referenc…

This paper introduces RealDESED, a new benchmark for domestic sound event detection with 5,710 recordings, precise annotations, and multi-annotator labeling.

The paper introduces VRSafe, a novel virtual QWERTY keyboard designed to significantly mitigate keystroke inference attacks in virtual reality by introducing false positive keystrokes and incorporatin…

The paper introduces CaReCoS, a benchmark for multimodal reasoning over medical acoustic spectrograms, and evaluates the performance of vision and omni models, finding a maximum accuracy of 51.2%.

This paper introduces SSTMark, a training-free speech watermarking framework that encodes watermark information into the semantic content of generated speech.

This paper proposes a new training criterion to reduce a classifier's reliance on shortcuts in language proficiency assessment systems, improving their correlation with human references.

This paper introduces WanSong, a diffusion-based model for long-form, commercial-grade song generation that directly generates high-fidelity, multilingual songs up to 5 minutes and outputs dual stems,…

This paper introduces Audio BERT (AuB) and SpInv, methods for recovering embeddings from speech tokens and performing speaker inversion attacks using only three seconds of frontend output.

The paper introduces AudioHijack, a framework that successfully demonstrates context-agnostic and imperceptible auditory prompt injection attacks, showing that commercial Large Audio-Language Models c…

The paper proposes two novel CAPTCHA types—ASCII art and overlapping audio—and demonstrates that current frontier LLMs struggle significantly to solve them, suggesting they are highly effective anti-b…

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…