ECC isn't a direct mitigation against Rowhammer attacks, as memory errors caused by three or more flipped bits would still go undetected (unless you're using ChipKill, but that's a rare setup).

However, flipped three bits simultaneously isn't trivial, and the attempts that flip fewer bits will be detected and logged.

Isn't ChipKill just another form of ECC? If so there is a number of bitflips that ChipKill can no longer correct / detect. [1] seems to say that they observed some flips in dRAM with ChipKill, although the paper is a bit vague here.

[1] B. Schroeder et al, DRAM Errors in the Wild: A Large-Scale Field Study http://www.cs.toronto.edu/~bianca/papers/sigmetrics09.pdf

Right! Section 1.3 of this publication discusses possible mitigations for the row hammer problem and where ECC fits in

https://users.ece.cmu.edu/~omutlu/pub/rowhammer-summary.pdf

The paper you cite is from 2014 and the mitigations discussed there have all been circumvented. [1] is from 2020 and a better read for Rowhammer mitigation.

[1] J. S. Kim et al, Revisiting RowHammer: An Experimental Analysis of Modern DRAM Devices and Mitigation Techniques https://arxiv.org/abs/2005.13121

Thanks for pointing that out!