Zihao Zhu

Awesome-Backdoor-in-Deep-Learning. A curated list of papers & resources on backdoor attacks and defenses in deep learning.

unthinking_vulnerability. To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

EARBench. Benchmarking Physical Risk Awareness of Foundation Model-based Embodied AI Agents

vdc. This is the official implementation of ICLR 2024 paper "VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models".