Dynamic Rowhammer Threshold Management:Temperature-Aware Threshold Degradation for In-DRAM Defenses
2026-07-11 • Hardware Architecture
Hardware ArchitectureCryptography and Security
AI summaryⓘ
The authors studied a problem called Rowhammer, where certain memory cells in DRAM can cause errors when accessed repeatedly. They noticed that the threshold for these errors changes with temperature, but current defenses set this threshold only once when the memory is made. To fix this, the authors created a method that adjusts the defense thresholds dynamically based on the current temperature, improving accuracy. Their approach reduces error breaches significantly in several defense techniques without adding much delay. They also show their method helps diagnose limitations in specific defenses like TRR.
RowhammerDRAMmemory errorsruntime temperaturethreshold managementSALT-CPRACTRRdefense mechanismslatency
Authors
Aziz Alajmi, Hoeseok Yang
Abstract
In-DRAM Rowhammer defenses pin the mitigation threshold at manufacture time, yet the true Rowhammer Threshold (TRHD) varies with runtime temperature. We propose \emph{Dynamic Rowhammer Threshold Management}, a defense-agnostic runtime layer that re-sources each defense's threshold from the observed temperature once per epoch via a linear-$T$ model with a VRD-motivated guardband $g$, projecting the result onto SALT-C, PRAC, and TRR through each defense's threshold parameter. A decoupled oracle that scales physical TRHD per-DIMM by $δ\sim \mathrm{N}(1, σ)$ breaks model self-consistency. The layer drives PRAC's 72 staleness breaches at 85$^\circ$C to zero; at $σ{=}0.10$, sweeping $g$ collapses PRAC breaches from 38.4 ($g{=}1.0$) to 9.6 ($g{=}0.9$). SALT-C drops from 10 nominal-static breaches to 2 (Dynamic) to 0 (bootstrap), at $\leq$5.1\% latency. TRR is capacity-limited; the layer acts as a diagnostic.