ALARM: Active LeArning of Rowhammer Mitigations

TL;DR

This paper introduces ALARM, an active learning-based tool that automatically infers parameters of Rowhammer mitigations in DRAM, aiding evaluation without manufacturer disclosure.

Contribution

The paper presents a novel active learning approach to automatically infer Rowhammer mitigation parameters, addressing the lack of transparency from DRAM manufacturers.

Findings

Successfully infers mitigation parameters for synthetic DRAM models

Enhances understanding of mitigation effectiveness

Provides a tool for evaluating DRAM security measures

Abstract

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.