# RowHammer: A Retrospective

arXiv: https://arxiv.org/abs/1904.09724 · HTML: https://mlsanity.com/paper/1904.09724/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2019.

## Built on by (most cited first, 19 of 19)

- [Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems](https://mlsanity.com/paper/2405.06624/) (2024)
- [DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories](https://mlsanity.com/paper/2111.04625/) (2021)
- [Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead](https://mlsanity.com/paper/2101.02559/) (2021)
- [TrojViT: Trojan Insertion in Vision Transformers](https://mlsanity.com/paper/2208.13049/) (2022)
- [LLM for SoC Security: A Paradigm Shift](https://mlsanity.com/paper/2310.06046/) (2023)
- [GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs](https://mlsanity.com/paper/2411.13757/) (2024)
- [ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack](https://mlsanity.com/paper/2111.01080/) (2021)
- [DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks](https://mlsanity.com/paper/2405.13891/) (2024)
- [On the Relationship Between Robustness and Expressivity of Graph Neural Networks](https://mlsanity.com/paper/2504.13786/) (2025)
- [Verification of Bit-Flip Attacks against Quantized Neural Networks](https://mlsanity.com/paper/2502.16286/) (2025)
- [BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models](https://mlsanity.com/paper/2505.16670/) (2025)
- [DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers](https://mlsanity.com/paper/2407.21220/) (2024)
- [SoK: A Systems Perspective on Compound AI Threats and Countermeasures](https://mlsanity.com/paper/2411.13459/) (2024)
- [SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Models](https://mlsanity.com/paper/2509.17371/) (2025)
- [FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models](https://mlsanity.com/paper/2510.24985/) (2025)
- [FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement Learning](https://mlsanity.com/paper/2512.09872/) (2025)
- [Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent](https://mlsanity.com/paper/2311.01205/) (2023)
- [RMF: A Risk Measurement Framework for Machine Learning Models](https://mlsanity.com/paper/2406.12929/) (2024)
- [Remote Rowhammer Attack using Adversarial Observations on Federated Learning Clients](https://mlsanity.com/paper/2505.06335/) (2025)

## Abstract (arXiv)

This retrospective paper describes the RowHammer problem in Dynamic Random Access Memory (DRAM), which was initially introduced by Kim et al. at the ISCA 2014 conference~citerowhammer-isca2014. RowHammer is a prime (and perhaps the first) example of how a circuit-level failure mechanism can cause a practical and widespread system security vulnerability. It is the phenomenon that repeatedly accessing a row in a modern DRAM chip causes bit flips in physically-adjacent rows at consistently predictable bit locations. RowHammer is caused by a hardware failure mechanism called em DRAM disturbance errors, which is a manifestation of circuit-level cell-to-cell interference in a scaled memory technology. Researchers from Google Project Zero demonstrated in 2015 that this hardware failure mechanism can be effectively exploited by user-level programs to gain kernel privileges on real systems. Many other follow-up works demonstrated other practical attacks exploiting RowHammer. In this article, we comprehensively survey the scientific literature on RowHammer-based attacks as well as mitigation techniques to prevent RowHammer. We also discuss what other related vulnerabilities may be lurking in DRAM and other types of memories, e.g., NAND flash memory or Phase Change Memory, that can potentially threaten the foundations of secure systems, as the memory technologies scale to higher densities. We conclude by describing and advocating a principled approach to memory reliability and security research that can enable us to better anticipate and prevent such vulnerabilities.