arXiv Machine Learning
SE-ADD: Self-Evolving Audio Deepfake Detection with Mistake-Driven Supervision
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 4
FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors
arXiv:2606. 05101v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models.
arXiv Machine Learning
2d ago
SEAR: Spoofing Evidence-Grounded Audio Reasoning Benchmark for Audio Language Models
arXiv:2609.39847v1 Announce Type: cross Abstract: Audio language models (ALMs) are increasingly used for audio deepfake detection (ADD), yet existing benchmarks assess their verdicts or rationale pla...
arXiv AI
Sep 12
Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
The paper introduces the Spectral Masking and Interpolation Attack (SMIA), a black‑box adversarial technique that subtly alters inaudible frequency regions of AI‑generated audio to fool voice authentication systems and their countermeasures. Experiments show SMIA achieves at least 82% success against combined verification and countermeasure systems, 97.5% against standalone speaker verification, and 100% against countermeasures, revealing a critical security gap. The authors argue that current static defenses are inadequate and call for dynamic, context‑aware defenses that can adapt to evolving threats.
arXiv AI
Aug 20
`From Prompt to Perturbation': An Adaptive Framework for Voice-Based Jailbreaks on Audio LLMs
The paper introduces an adaptive jailbreak attack framework that evaluates both cascaded pipelines and end‑to‑end large audio‑language models (LALMs) under a unified setting. It employs a feedback‑guided mutation engine to automatically generate and refine jailbreak candidates across textual prompts and audio perturbations, thereby broadening attack diversity. Experiments on six audio‑based systems show that both paradigms remain highly vulnerable, with the framework achieving higher attack success rates than existing methods.
arXiv AI
Aug 11
MADBench: A Benchmark for Modality-Aware Audio Deepfake Detection
arXiv:2608. 09593v1 Announce Type: cross Abstract: Recent advances in speech synthesis and audio generation have made high-fidelity acoustic forgery low-cost and difficult to attribute, enabling a realistic attack scenario in which speech and background audio are independently manipulated over otherwise authentic video.
arXiv AI
Jun 30
Proteus: Automated Adversarial Robustness Testing for Audio Deepfake Detectors
arXiv:2606. 29544v1 Announce Type: cross Abstract: We present Proteus, a framework developed at Resemble AI for automated robustness testing of our audio deepfake detection system.