SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech
cs.SD, cs.CL, eess.AS
Submitted: 2026-06-04
Updated: 2026-08-29
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- On the Opportunities and Risks of Foundation Models
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?
- Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models
- TranslateGemma Technical Report
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
- SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models
- Gemma 3 Technical Report
- Voice Jailbreak Attacks Against GPT-4o
- DeepInception: Hypnotize Large Language Model to Be Jailbreaker
- Voxtral
- SALMONN: Towards Generic Hearing Abilities for Large Language Models
- GPT-4o System Card
- Can Large Language Models Understand, Reason About, and Generate Code-Switched Text?
- Qwen2.5-Omni Technical Report
- Qwen3-Omni Technical Report
- Low-Resource Languages Jailbreak GPT-4
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
- WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
- Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment