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:2603. 19127v2 Announce Type: replace Abstract: As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone while introducing an expanded attack surface.
arXiv:2602. 02557v2 Announce Type: replace-cross Abstract: Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignment.
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:2604. 09222v2 Announce Type: replace-cross Abstract: Audio Large Language Models (ALLMs) enable spoken interaction but introduce new jailbreak vulnerabilities.
arXiv:2608. 10405v1 Announce Type: cross Abstract: Many studies have shown that specially crafted inputs can induce large language models (LLMs) to generate excessively long outputs, resulting in significant computational overhead and resource consumption.
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:2506. 22666v3 Announce Type: replace-cross Abstract: The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabilities in real-world settings.
arXiv:2606.06037v3 Announce Type: replace-cross Abstract: Large audio language models (LALMs) are increasingly deployed in real-world applications, yet their safety alignment is still primarily evalu...
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.
The paper investigates poisoning-based backdoor attacks on Speech Emotion Recognition (SER) systems that use self‑supervised acoustic representations. It introduces a stealthy, low‑energy acoustic trigger that can be embedded imperceptibly into both natural and synthetic speech, enabling scalable poisoning. Experiments show high attack success rates with low poisoning ratios, cross‑model transferability, and a particular vulnerability of self‑supervised representations, highlighting the lowered barrier to effective backdoor attacks via TTS technology.
arXiv:2606. 06833v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) systems operating in real-time settings must process acoustic input under strict temporal constraints, where transcription decisions are inherently made on incomplete information.
arXiv:2607. 01702v1 Announce Type: cross Abstract: Recently, speech classification methods have gained widespread adoption in intelligent gadgets.