Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
DuplexJail: Safety Alignment Breaks Under Spoken Interruption in Full-Duplex Models
Jaechul Roh, Deepak Chandran, Amir Houmansadr +1
Full-duplex speech models accept user speech while generating responses, creating an underexplored attack surface. We introduce DuplexJail, which delivers fixed, request-independen…
cs.CR2026
Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
Jaechul Roh, Amir Houmansadr
Prior work shows that fine-tuning aligned models on benign data degrades safety in text and vision modalities, and that proximity to harmful content in representation space predict…
cs.CR2023
Memory Triggers: Unveiling Memorization in Text-To-Image Generative Models through Word-Level Duplication
Ali Naseh, Jaechul Roh, Amir Houmansadr
Diffusion-based models, such as the Stable Diffusion model, have revolutionized text-to-image synthesis with their ability to produce high-quality, high-resolution images. These ad…