Analysis of GPU Memory Vulnerabilities

Graphics processing units (GPUs) have become a widely used technology for various purposes. While their intended use is accelerating graphics rendering, their parallel computing capabilities have expanded their use into other areas. They are used in computer gaming, deep learning for artificial intelligence and mining cryptocurrencies. Their rise in popularity led to research involving several security aspects, including this paper’s focus, memory vulnerabilities. Research documented many vulnerabilities, including GPUs not implementing address space layout randomization, not zeroing out memory after deallocation, and not initializing newly allocated memory. These vulnerabilities can lead to a victim’s sensitive data being leaked to an attacker, an impactful threat considering the usages of GPU computing presented. In this paper, we attempt to implement these vulnerabilities on an NVIDIA GPU to determine if any advancements in memory architecture have been made since the documentation of such vulnerabilities. This work demonstrates that the lack of attention to security in early GPU development has been adjusted to appropriately match a level of concern for a computing component that numerous industries rely on