1. This article introduces a new classification of cache covert channel attacks: Hit+Miss, Hit+Hit, and Miss+Miss.
2. It presents a way in which the dirty bits in cache lines can be used as timing-based cache channels for leaking information without shared memory between the sender and receiver.
3. It evaluates the transmission rates and bit error rates of WB covert channels, compares it with existing cache channels from the perspectives of stability and stealthiness, and proposes possible defenses against this type of attack.
The article is generally reliable and trustworthy in its presentation of the new classification of cache covert channel attacks, its description of how to use dirty bits in cache lines as timing-based channels for leaking information without shared memory between sender and receiver, its evaluation of transmission rates and bit error rates of WB covert channels, its comparison with existing cache channels from the perspectives of stability and stealthiness, and its proposal for possible defenses against this type of attack. The authors provide evidence to support their claims throughout the article by citing relevant research papers.
However, there are some potential biases that should be noted. For example, while the authors discuss various forms of side-channel attack at the end of the paper, they do not explore counterarguments or present both sides equally. Additionally, there is no discussion about possible risks associated with using these types of attacks or any mention about ethical considerations when using them. Furthermore, while the authors provide evidence to support their claims throughout the article by citing relevant research papers, they do not provide any evidence for their own claims or any data to back up their conclusions.
In conclusion, while this article is generally reliable and trustworthy in its presentation of new classifications for cache covert channel attacks as well as its evaluation and comparison with existing ones from different perspectives, there are some potential biases that should be noted such as lack of exploration into counterarguments or risks associated with using these types of attacks as well as lack of evidence to back up their own claims or conclusions.