Nethammer: Inducing Rowhammer Faults through Network Requests

In this paper, we present Nethammer, a remote Rowhammer attack without a single attacker-controlled line of code on the targeted system, i.e., not even JavaScript. Nethammer works on commodity consumer-grade systems that either are protected with quality-of-service techniques like Intel CAT or that use uncached memory, flush instructions, or non-temporal instructions while handling network requests (e.g., for interaction with the network device). We demonstrate that the frequency of the cache misses is in all three cases high enough to induce bit flips. Our evaluation showed that depending on the location, the bit flip compromises either the security and integrity of the system and the data of its users, or it can leave persistent damage on the system, i.e., persistent denial of service. We invalidate threat models of Rowhammer defenses building upon the assumption of a local attacker. Consequently, we show that most state-of-the-art defenses do not affect our attack. In particular, we demonstrate that target-row-refresh (TRR) implemented in DDR4 has no aggravating effect on local or remote Rowhammer attacks.