This article, from 2019, shows a major flaw in the intel CPU’s that allow them to be exploited remotely overt the networks without requiring the attacker to have physical access or any malware installed on the target computer. The attacker works by using Netcat to sniff out sensitive data from intels cpu cache. It works by sending specially crafted network packets to a target computer that has the remote direct memory access feature enabled. RDMA allows attackers to spy on remote peripherals such as network cards in order to observe the timing difference between a network packet that is served from the remote processor cache versus a packet served from memory. By measuring the inter-arrival timing of packets, Netcat is able to use keystroke timing attack to leak what you type. The keystroke attack is correct about 85% of the time as of the writing of this article.
“NetCAT: New Attack Lets Hackers Remotely Steal Data From Intel CPUs.” The Hacker News, 11 Sept. 2019, thehackernews.com/2019/09/netcat-intel-side-channel.html?m=1.