Showing cs.CRShow all
2 papers · 1 filter
cs.CR2025
Provable Repair of Deep Neural Network Defects by Preimage Synthesis and Property Refinement
Jianan Ma, Jingyi Wang, Qi Xuan +1
It is known that deep neural networks may exhibit dangerous behaviors under various security threats (e.g., backdoor attacks, adversarial attacks and safety property violation) and…
cs.CR2023
HODOR: Shrinking Attack Surface on Node.js via System Call Limitation
Wenya Wang, Xingwei Lin, Jingyi Wang +4
Node.js provides Node.js applications with system interaction capabilities using system calls. However, such convenience comes with a price, i.e., the attack surface of JavaScript…