TrojanNet – a simple yet effective attack on machine learning models

Injecting malicious backdoors into deep neural networks is easier than previously thought, a new study by researchers at Texas A&M University shows. There's growing concern about the security implications of deep learning algorithms, which are becoming an integral part of applications across different sectors. Vulnerabilities in deep neural networks (DNN), the main technology behind deep learning, has become a growing area of interest in recent years. Trojan attacks are hidden triggers embedded in neural networks that can cause an AI model to act erratically at the whim of a malicious actor. For instance, an attacker can fool the image processor of a self-driving car into bypassing a stop sign or mistaking it for a speed limit sign.