4 papers
T-IMPACT: A Severity-Aware Benchmark for Contextual Image-Text Manipulation
Gagandeep Singh, Aaditya Yadav, Priyanka Singh
Recent advances in vision-language models and generative editing systems have made it increasingly easy to produce persuasive multimodal misinformation by altering images, text, or…
TRAP: Targeted Redirecting of Agentic Preferences
Hangoo Kang, Jehyeok Yeon, Gagandeep Singh
Autonomous agentic AI systems powered by vision-language models (VLMs) are rapidly advancing toward real-world deployment, yet their cross-modal reasoning capabilities introduce ne…
Learning a Pessimistic Reward Model in RLHF
Yinglun Xu, Hangoo Kang, Tarun Suresh +2
This work proposes `PET', a novel pessimistic reward fine-tuning method, to learn a pessimistic reward model robust against reward hacking in offline reinforcement learning from hu…
Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment
Jason Vega, Junsheng Huang, Gaokai Zhang +3
Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety…