2 papers
cs.CR2026
GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents
Xueyi Li, Zhuoneng Zhou, Zitao Liu +1
Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boostin…
eess.AS2026
XLSR-MamBo: Scaling the Hybrid Mamba-Attention Backbone for Audio Deepfake Detection
Kwok-Ho Ng, Tingting Song, Yongdong Wu +1
Advanced speech synthesis technologies have enabled highly realistic speech generation, posing security risks that motivate research into audio deepfake detection (ADD). While stat…