This paper challenges the existing victim-focused counter-based RowHammer detection mechanisms by experimentally demonstrating a novel multi-sided fault injection attack technique called Threshold Breaker. This mechanism can effectively bypass the most advanced counter-based defense mechanisms by soft-attacking the rows at a farther physical distance from the target rows. While no prior work has demonstrated the effect of such an attack, our work closes this gap by systematically testing 128 real commercial DDR4 DRAM products and reveals that the Threshold Breaker affects various chips from major DRAM manufacturers. As a case study, we compare the performance efficiency between our mechanism and a well-known double-sided attack by performing adversarial weight attacks on a modern Deep Neural Network (DNN). The results demonstrate that the Threshold Breaker can deliberately deplete the intelligence of the targeted DNN system while DRAM is fully protected.

翻译：本文通过实验性展示一种名为“阈值突破者”的新型多侧面故障注入攻击技术，挑战了现有以受害者为中心的基于计数器的RowHammer检测机制。该机制通过软性攻击远离目标行的物理距离更远的行，能够有效绕过最先进的基于计数器的防御机制。尽管此前尚无研究展示此类攻击的效果，我们的工作通过系统测试128个真实商用DDR4 DRAM产品填补了这一空白，并揭示了“阈值突破者”影响了来自主要DRAM制造商的各种芯片。作为案例研究，我们通过对现代深度神经网络执行对抗性权重攻击，比较了我们机制与已知双面攻击之间的性能效率。结果表明，在DRAM完全受保护的情况下，“阈值突破者”能够蓄意削弱目标DNN系统的智能性。