AEGIS：利用内部信号实现音频内生防护，抵御大型音频语言模型越狱

Computer Science > Sound arXiv:2609.29287 (cs) [Submitted on 24 Sep 2026] Title:AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks Authors:Yu-Ling Liao, Tzu-Chin Chiu, Zong-You Chen, Chi-Lei Tsai, Shao-Yuan Lo View a PDF of the paper titled AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks, by Yu-Ling Liao and 4 other authors View PDF HTML (experimental) Abstract:Large audio-language models (LALMs) expand language models to process and interpret audio, but also expose them to heterogeneous audio jailbreaks. We ask whether successful jailbreaks reflect failures to recognize harmful intent or failures occurring after such recognition. Layer-wise probing reveals the latter: risk-related information remains decodable from intermediate representations, yet the internal risk signal fails to translate into refusal in later-layer processing. We identify this discrepancy as the risk-to-refusal gap. Building on this finding, we propose AEGIS, a detect-then-intervene defense whose mid-layer risk gate selectively activates downstream safety adapters. Across six LALMs and three heterogeneous audio jailbreak benchmarks, AEGIS reduces the average unsafe rate from 17.9% to 0.4%, while causing only a marginal increase in over-refusal on benign inputs. These results establish selective internal intervention as an effective path toward more robust refusal in LALMs. The code is available at this https URL. Comments: Subjects: Sound (cs.SD); Cryptography and Security (cs.CR) Cite as: arXiv:2609.29287 [cs.SD] (or arXiv:2609.29287v1 [cs.SD] for this version) https://doi.org/10.48550/arXiv.2609.29287 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Yu-Ling Liao [view email] [v1] Thu, 24 Sep 2026 09:24:13 UTC (112 KB) Full-text links: Access Paper: View a PDF of the paper titled AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks, by Yu-Ling Liao and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.SD new | recent | 2026-09 Change to browse by: cs cs.CR References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)