10 papers
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…
Bob's Confetti: Phonetic Memorization Attacks in Music and Video Generation
Jaechul Roh, Zachary Novack, Yuefeng Peng +3
Generative AI systems for music and video commonly use text-based filters to prevent regurgitation of copyrighted material. We expose a significant vulnerability in this approach b…
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…
OverThink: Slowdown Attacks on Reasoning LLMs
Abhinav Kumar, Jaechul Roh, Ali Naseh +4
Most flagship language models generate explicit reasoning chains, enabling inference-time scaling. However, producing these reasoning chains increases token usage (i.e., reasoning…
World-To-Image: Grounding Text-to-Image Generation with Agent-Driven World Knowledge
Moo Hyun Son, Jintaek Oh, Sun Bin Mun +2
While text-to-image (T2I) models can synthesize high-quality images, their performance degrades significantly when prompted with novel or out-of-distribution (OOD) entities due to…
Throttling Web Agents Using Reasoning Gates
Abhinav Kumar, Jaechul Roh, Ali Naseh +2
AI web agents use Internet resources at far greater speed, scale, and complexity -- changing how users and services interact. Deployed maliciously or erroneously, these agents coul…