# ALARM: Active LeArning of Rowhammer Mitigations

arXiv: https://arxiv.org/abs/2211.16942 · HTML: https://mlsanity.com/paper/2211.16942/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 36 references that are in the map.
- First posted on arXiv 30 Nov 2022.

## Builds on (most cited first, 4 of 4)

- [Uncovering In-DRAM RowHammer Protection Mechanisms: A New Methodology, Custom RowHammer Patterns, and Implications](https://mlsanity.com/paper/2110.10603/) (2021)
- [Prognosis: Closed-Box Analysis of Network Protocol Implementations](https://mlsanity.com/paper/2201.02577/) (2021)
- [CacheQuery: Learning Replacement Policies from Hardware Caches](https://mlsanity.com/paper/1912.09770/) (2019)
- [SoftMC: Practical DRAM Characterization Using an FPGA-Based Infrastructure](https://mlsanity.com/paper/1805.03195/) (2018)

## Abstract (arXiv)

Rowhammer is a serious security problem of contemporary dynamic random-access memory (DRAM) where reads or writes of bits can flip other bits. DRAM manufacturers add mitigations, but don't disclose details, making it difficult for customers to evaluate their efficacy. We present a tool, based on active learning, that automatically infers parameter of Rowhammer mitigations against synthetic models of modern DRAM.