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 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 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…

The paper proposes Domain-Aware Sharpness Minimization (DASM), a novel optimizer that enhances the robustness and generalization of voice stream steganalysis models across varying data distributions.

This paper investigates how Byte-Pair Encoding (BPE) tokenization causes Code LLMs to disproportionately memorize certain types of secrets, a phenomenon termed 'gibberish bias'.

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 an attention-augmented LSTM model can achieve near-perfect character-level decipherment of homophonic ciphertexts from historical English and Swedish, even under challengin…

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…

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 compares two sparse autoencoder architectures, finding that Differential SAEs (Diff-SAE) significantly outperform Crosscoders in isolating backdoor-related features in language models.

The paper proposes ChaRVoC, a novel Challenge-Response Voice Cancelable authentication system that enhances voice biometrics by integrating inherent voice features, secret keys, and dynamic challenges…

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

This paper conducts a structured ablation study using a unified threat model to evaluate how various system factors (like model architecture and retrieval configuration) influence different types of p…

The paper introduces CyBiasBench, a comprehensive benchmark that quantifies the inherent, agent-specific bias in LLM agents' attack selection patterns in cybersecurity scenarios.

The paper systematically evaluates various defense mechanisms against persistent memory attacks on LLM agents, finding that only tool-gating at the memory layer (Memory Sandbox) effectively mitigates…

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…