3 papers
cs.CL2025
When Safety Blocks Sense: Measuring Semantic Confusion in LLM Refusals
Riad Ahmed Anonto, Md Labid Al Nahiyan, Md Tanvir Hassan
Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores t…
cs.CR2025
Identifying and Addressing User-level Security Concerns in Smart Homes Using "Smaller" LLMs
Hafijul Hoque Chowdhury, Riad Ahmed Anonto, Sourov Jajodia +2
With the rapid growth of smart home IoT devices, users are increasingly exposed to various security risks, as evident from recent studies. While seeking answers to know more on tho…
cs.CV2025
DFCon: Attention-Driven Supervised Contrastive Learning for Robust Deepfake Detection
MD Sadik Hossain Shanto, Mahir Labib Dihan, Souvik Ghosh +8
This report presents our approach for the IEEE SP Cup 2025: Deepfake Face Detection in the Wild (DFWild-Cup), focusing on detecting deepfakes across diverse datasets. Our methodolo…