arXiv:2603. 10725v3 Announce Type: replace-cross Abstract: The modern generative audio models can be used by an adversary in an unlawful manner, specifically, to impersonate other people to gain access to private information.
arXiv:2606. 10246v1 Announce Type: cross Abstract: Maliciously-created fake speech, including deepfaked and spoofed audio, is proliferating at an alarming rate, and detection models are racing to stay ahead of the curve.
arXiv:2607. 14753v1 Announce Type: cross Abstract: Recent advances in text-to-speech and voice cloning make high-quality spoofing inexpensive and scalable, threatening voice authentication systems, especially automatic speaker verification (ASV).
ToolDF is a tool‑integrated reasoning framework designed for detecting mixed‑authenticity audio deepfakes, where genuine and manipulated audio cues coexist across time or overlapping sources. It uses an audio large language model to orchestrate tasks such as source separation and routing to domain‑specific experts, aggregating their evidence into an interpretable verdict. The authors also introduce a mixed‑authenticity ADD benchmark and report that ToolDF outperforms monolithic baselines, achieving significant macro‑F1 gains while localizing evidence to specific temporal regions and acoustic sources.
arXiv:2606. 16137v1 Announce Type: cross Abstract: Speech deepfake detection (SDD) systems require trustworthy explanations for reliable decision-making.
The paper reviews how voice authentication has evolved from handcrafted acoustic features to deep learning speaker embeddings, expanding its use in finance, smart devices, and law enforcement. It surveys modern threats—including data poisoning, adversarial, deepfake, and adversarial spoofing attacks—tracing their development alongside technological advances. For each attack type, the authors summarize methods, datasets, performance, and limitations, and organize the literature using accepted taxonomies to highlight emerging risks and open challenges.
arXiv:2606. 14466v1 Announce Type: cross Abstract: This paper investigates the fragility of post-hoc explanation methods in audio deepfake detection.
arXiv:2608. 15411v1 Announce Type: new Abstract: The ability of artificial intelligence (AI) models to generate highly realistic human voices has advanced rapidly.
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:2608.29120v1 Announce Type: cross Abstract: Speech Language Models (SLMs) are increasingly deployed in multi-speaker environments, yet their ability to attribute speech to the correct speaker a...
arXiv:2609.13842v1 Announce Type: cross Abstract: Recent advances in speech synthesis and voice conversion have made deepfake speech increasingly realistic, making generalization to unseen spoofing a...
The paper introduces DF‑CAPTCHA, an active defense that asks callers to complete simple challenge‑response tasks during voice and video calls. By evaluating responses on realism, identity consistency, task completion, and response time, the system can detect real‑time deepfake impersonations. Experiments across audio and video modalities show that DF‑CAPTCHA outperforms passive artifact‑search methods, achieving high accuracy and demonstrating the effectiveness of challenge‑based verification against next‑generation social engineering attacks.
arXiv:2606. 10912v1 Announce Type: cross Abstract: Deepfake speech detectors often output a single score without explaining why an audio sample is flagged, where in the signal the evidence lies, or what cues drive the decision.