Audio Large Language Models (ALLMs) enable spoken interaction but introduce new jailbreak vulnerabilities. Existing perturbation-based jailbreaks do not explicitly control which frequency bands car...
<p><strong>Tác giả:</strong> Yunqiang Wang, Hengyuan Na, Di Wu, Miao Hu, Guocong Quan</p>
<p>Audio Large Language Models (ALLMs) enable spoken interaction but introduce new jailbreak vulnerabilities. Existing perturbation-based jailbreaks do not explicitly control which frequency bands carry the perturbation. Although such perturbations can elicit unsafe responses, repeatedly applying a universal perturbation across diverse inputs may also degrade utility on normal tasks, leaving a conspicuous behavioral footprint that may expose the attack to users or automated monitoring systems an...</p>
<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.1145/3767308.3835479" target="_blank" rel="noopener">https://doi.org/10.1145/3767308.3835479</a></p>
<p>📖 <a href="https://doi.org/https://doi.org/10.1145/3767308.3835479" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>
Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex
