Loaded Dice: Solving the Non-Selection Problem for Scalable Probabilistic RowHammer Defense

2026-05-17

AI Summary

This work addresses the excessive mitigation overhead incurred by existing probabilistic RowHammer defenses under low attack thresholds, a consequence of the “non-selectivity problem” that severely degrades memory bandwidth. To overcome this limitation, the authors propose PrISM, the first defense mechanism incorporating a cross-window historical sampling correlation scheme. PrISM employs a Sampled History Queue (SHQ) to identify rows exhibiting sustained high activation rates and activates enhanced mitigation only when necessary via an Alert Back-Off protocol. Notably, PrISM requires no DRAM modifications or per-row counters, utilizing merely 625 bytes of SRAM per bank. Experimental results demonstrate that at a threshold of 500, PrISM incurs an average performance overhead of just 0.2%—significantly lower than PRAC’s 14%—and at a threshold of 250, it reduces average latency from MINT’s 10.7% to 1.5%, achieving a 7.1× reduction in overhead while maintaining robust protection.

Abstract

DRAM scaling has exacerbated the RowHammer vulnerability. To counter this, JEDEC recently introduced Per Row Activation Counting (PRAC) with the Alert Back-Off protocol as an optional DDR5 feature. While promising, PRAC requires per-row counter cells that incur area overhead, and updating them on every activation lengthens DRAM timing parameters, degrading performance. Probabilistic mitigations such as MINT offer a lower-cost alternative by randomly selecting and mitigating rows within periodic mitigation windows. MINT is effective at higher thresholds (>= 1000), but at lower thresholds, it must raise its mitigation rate to overcome the non-selection problem, where heavily hammered rows can repeatedly escape sampling. This fixed-rate scaling reduces effective memory bandwidth even when no attack is present. To overcome this limitation, we propose PrISM, an intersection-based probabilistic mitigation that correlates sampled rows across windows using a Sampled History Queue (SHQ). PrISM samples a few activation slots per window, stores sampled-but-unmitigated rows in the SHQ, and requests an additional mitigation through the existing Alert Back-Off protocol when a sampled row reappears in this history. This allows PrISM to increase mitigation only when persistent row activity is observed, without globally increasing the fixed mitigation rate. At the threshold of 500, PrISM incurs a negligible 0.2% average slowdown compared to 14% for PRAC, with no DRAM array changes or per-row counters and only 625B of SRAM per bank, one to two orders of magnitude less than prior secure counter-based in-DRAM defenses. Compared to MINT, PrISM provides better scalability at low thresholds, reducing average slowdown from 10.7% to 1.5% at a threshold of 250, a 7.1x reduction. PrISM is open-sourced at https://github.com/STAR-Laboratory/prism.

Problem

• RowHammer
• non-selection problem
• probabilistic mitigation
• DRAM security
• memory bandwidth

Innovation

• Probabilistic RowHammer Defense
• Non-Selection Problem
• Sampled History Queue
• PrISM
• Low-Overhead Mitigation