Securing DRAM at Scale: ARFM-Driven Row Hammer Defense with Unveiling the Threat of Short tRC Patterns

2025-01-24

AI Summary

Row Hammer (RH) attacks pose escalating threats to DRAM, particularly under short tRC modes that significantly increase attack success rates. To address this, we propose MARC—a lightweight hardware IP implementing a novel tRC-density-aware Adaptive Row Refresh Management (ARFM) scheduling mechanism. MARC integrates probabilistic and counter-based RH tracking, deployed co-located on both the DRAM die and memory controller for tightly coupled, zero-overhead real-time mitigation. It is the first work to quantitatively characterize the security risk of short tRC modes, achieving >99% detection accuracy with only 3,363 μm² hardware area and negligible power overhead. Experimental results show that on-die deployment reduces the maximum RH exposure window by 8.1× (probabilistic) and 1.5× (counter-based), while controller-side deployment improves defense efficiency against PARA and Graphene by 50× and 5.7×, respectively.

Technology Category

• Machine Learning: Hardware-aware ML
• Application Domains: Security
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

To address the issue of powerful row hammer (RH) attacks, our study involved an extensive analysis of the prevalent attack patterns in the field. We discovered a strong correlation between the timing and density of the active-to-active command period, ${tRC}$, and the likelihood of RH attacks. In this paper, we introduce MARC, an innovative ARFM-driven RH mitigation IP that significantly reinforces existing RH mitigation IPs. MARC dynamically adjusts the frequency of RFM in response to the severity of the RH attack environment, offering a tailored security solution that not only detects the threats but also adapts to varying threat levels. MARC's detection mechanism has demonstrated remarkable efficiency, identifying over 99% of attack patterns. Moreover, MARC is designed as a compact hardware module, facilitating tight integration either on the memory controller-side or DRAM-side within the memory system. It only occupies a negligible hardware area of 3363~ extit{$mu m^2$}. By activating ARFM based on MARC's detection, the additional energy overhead is also negligible in normal workloads. We conduct experiments to compare the highest row count throughout the patterns, defined as max exposure, between the vanilla RH mitigation IPs and the MARC-enhanced versions of the same IPs, focusing on both DRAM-side and memory controller-side. On the DRAM-side, MARC + probabilistic scheme and MARC + counter-based tracking scheme achieve 8.1$ imes$ and 1.5$ imes$ improvement in max exposure ratio compared to the vanilla IPs, respectively. On the memory controller-side, the MARC + PARA and MARC + Graphene achieve 50$ imes$ and 5.7$ imes$ improvement in max exposure ratio compared to the vanilla IPs, respectively. MARC ensures optimal security without sacrificing system performance, making MARC a pioneering solution in the realm of RH attack mitigation.

Problem

• DRAM Protection
• Row Hammer Attack
• Short tRC Mode

Innovation

• MARC
• Row Hammer Attack Resistance
• Energy-Efficient Hardware Solution