Long Hoang Pham

SOCRATES: Towards a Unified Platform for Neural Network Analysis

2020 · arXiv (Cornell University)

Studies show that neural networks, not unlike traditional programs, are subject to bugs, e.g., adversarial samples that cause classification errors and discriminatory instances that demonstrate the lack of fairness. Given that neural networks are increasingly …

Verifying Neural Networks Against Backdoor Attacks

2022 · Lecture notes in computer science

Abstract Neural networks have achieved state-of-the-art performance in solving many problems, including many applications in safety/security-critical systems. Researchers also discovered multiple security issues associated with neural networks. One of them is backdoor attacks, i.e., a …