The paper introduces ROGUE, a framework that builds robust audio deepfake detection workflows by combining multiple detection tools. ROGUE treats workflow creation as a sequential decision problem and uses a dual-agent system: a perturbation agent generates audio distortions while a policy agent selects and executes detection tools that are resilient to those perturbations. Experiments on several datasets and real-world corruptions show that ROGUE consistently outperforms strong baselines in robustness and generalization, demonstrating the value of adversarially optimized workflow generation for reliable deployment.
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.
arXiv:2503. 17577v2 Announce Type: replace-cross Abstract: Deepfakes have emerged as a widespread and rapidly escalating concern in generative AI, spanning images, audio, and videos.
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.
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:2607. 17761v1 Announce Type: cross Abstract: Recently, speech deepfake detection (SDD) has achieved significant progress.
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:2607. 01729v1 Announce Type: new Abstract: Deep learning models for speech classification are vulnerable to backdoor attacks, where malicious triggers cause misclassification at inference time.
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.
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: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).
arXiv:2603. 22590v2 Announce Type: replace Abstract: With the increasing deployment of automated and agentic systems, ensuring the adversarial robustness of automatic speech recognition (ASR) models has become highly relevant.
Recently, speech classification methods have gained widespread adoption in intelligent gadgets. Current study indicates that backdoor attacks provide a substantial security concern to these models, underscoring the pressing necessity to investigate additional potential attack techniques to expose and prevent such risks.