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

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.

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.

This paper tests the impact of acoustic factors on voice control systems and introduces a Dual-Form Signal to Noise Ratio to decouple source stealth from attack efficacy.

The paper introduces a novel Clean-Referenced Feature-Vocoder Attack, a black-box adversarial attack that perturbs high-level SSL feature representations instead of raw audio waveforms, achieving supe…

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 TRIDENT, a framework to restore a source speaker's identity from converted audio using a three-pronged architecture.

The paper introduces MARS, a novel meta-adversarial framework that significantly improves black-box adversarial attacks against state-of-the-art Singing Voice Deepfake Detection (SVDD) systems by esca…

The paper demonstrates that AI agents can conduct a secret, undetectable conversation by exchanging a key using a novel cryptographic primitive, even if they start with no shared secret.

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…

This paper proposes a neural audio watermarking method that embeds a message into the continuous latent representation of a codec-like speech autoencoder for improved codec robustness.

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…

The paper demonstrates that even a casual attacker with basic IT skills can perform sophisticated privacy attacks on smart-home networks, extracting detailed daily routines and personal information fr…

MelShield is a robust, in-generation audio watermarking framework that embeds identifiable signals into AI-generated speech in the Mel-spectrogram domain for reliable copyright protection and attribut…

This paper proposes a framework to protect speaker privacy in dementia detection speech recordings by introducing Cumulative Signal Attack (CSA) at the signal level and Gradient Reversal Layer (GRL) w…

The paper introduces ActInv and PAF to systematically analyze and quantify privacy leakage from intermediate activations during split inference of LLMs, proposing PriPert for enhanced defense.