Showing 2026Show all
3 papers · 1 filter
cs.CR2026
DuplexJail: Spoken Interruption Attacks on Full-Duplex Speech Models
Jaechul Roh, Deepak Chandran, Amir Houmansadr +1
Full-duplex speech models accept user speech while generating responses, making input timing a potential safety concern. We introduce DuplexJail, which delivers fixed, request-inde…
cs.CR2026
Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
Jaechul Roh, Amir Houmansadr, Virat Shejwalkar
Fine-tuning on benign data is known to degrade safety alignment in text and vision LLMs, but whether distinct input properties drive this vulnerability differently remains unclear.…
cs.AI2026
SPILLage: Agentic Oversharing on the Web
Jaechul Roh, Eugene Bagdasarian, Hamed Haddadi +1
LLM-powered agents are beginning to automate user's tasks across the open web, often with access to user resources such as emails and calendars. Unlike standard LLMs answering ques…