DRAMA: Exploiting DRAM Addressing for Cross-CPU Attacks
Not on the map. Why?
Abstract (arXiv)
In cloud computing environments, multiple tenants are often co-located on the same multi-processor system. Thus, preventing information leakage between tenants is crucial. While the hypervisor enforces software isolation, shared hardware, such as the CPU cache or memory bus, can leak sensitive information. For security reasons, shared memory between tenants is typically disabled. Furthermore, tenants often do not share a physical CPU. In this setting, cache attacks do not work and only a slow cross-CPU covert channel over the memory bus is known. In contrast, we demonstrate a high-speed covert channel as well as the first side-channel attack working across processors and without any shared memory. To build these attacks, we use the undocumented DRAM address mappings. We present two methods to reverse engineer the mapping of memory addresses to DRAM channels, ranks, and banks. One uses physical probing of the memory bus, the other runs entirely in software and is fully automated. Using this mapping, we introduce DRAMA attacks, a novel class of attacks that exploit the DRAM row buffer that is shared, even in multi-processor systems. Thus, our attacks work in the most restrictive environments. First, we build a covert channel with a capacity of up to 2 Mbps, which is three to four orders of magnitude faster than memory-bus-based channels. Second, we build a side-channel template attack that can automatically locate and monitor memory accesses. Third, we show how using the DRAM mappings improves existing attacks and in particular enables practical Rowhammer attacks on DDR4.
Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Nov 2015.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 1; 2023: 0; 2024: 2; 2025: 4; 2026: 2.
10 papers.
- 2022Threat Assessment in Machine Learning based Systemscited by 9
- 2021Don't Knock! Rowhammer at the Backdoor of DNN Modelscited by 6
- 2024PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flipscited by 5
- 2025BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Modelscited by 2
- 2024SoK: A Systems Perspective on Compound AI Threats and Countermeasurescited by 1
- 2025SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Modelscited by 1
- 2026PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systemscited by 1
- 2025PaniCar: Securing the Perception of Advanced Driving Assistance Systems Against Emergency Vehicle Lightingcited by 0
- 2025Remote Rowhammer Attack using Adversarial Observations on Federated Learning Clientscited by 0
- 2026Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Modelscited by 0
- 2026Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models26 Mar 2026
- 2026PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems11 Mar 2026
- 2025SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Models22 Sep 2025
- 2025BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models22 May 2025
- 2025Remote Rowhammer Attack using Adversarial Observations on Federated Learning Clients9 May 2025
- 2025PaniCar: Securing the Perception of Advanced Driving Assistance Systems Against Emergency Vehicle Lighting8 May 2025
- 2024PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips10 Dec 2024
- 2024SoK: A Systems Perspective on Compound AI Threats and Countermeasures20 Nov 2024
- 2022Threat Assessment in Machine Learning based Systems30 Jun 2022
- 2021Don't Knock! Rowhammer at the Backdoor of DNN Models14 Oct 2021