Naturally
Proj CDeepFuzz Paper Reading: PELICAN: Exploiting Backdoors of Naturally Trained Deep Learning Models In Binary Code Analysis
## Abstract 背景: 1. 本文研究的不是被恶意植入的后门,而是products of defects in training 2. 攻击模式: injecting some small fixed input pattern(backdoor) to induce misclassifi ......