RowHammer: A Retrospective
Not on the map. Why?
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.
Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Apr 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 1; 2023: 2; 2024: 6; 2025: 7.
19 papers.
Sort:
By area:
- 2024Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systemscited by 96
- 2021DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memoriescited by 42
- 2021Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Aheadcited by 41
- 2022TrojViT: Trojan Insertion in Vision Transformerscited by 31
- 2023LLM for SoC Security: A Paradigm Shiftcited by 22
- 2024GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMscited by 10
- 2021ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attackcited by 3
- 2024DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networkscited by 3
- 2025On the Relationship Between Robustness and Expressivity of Graph Neural Networkscited by 3
- 2025Verification of Bit-Flip Attacks against Quantized Neural Networkscited by 2
- 2025BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Modelscited by 2
- 2024DeepBaR: Fault Backdoor Attack on Deep Neural Network Layerscited by 1
7 more
- 2024SoK: A Systems Perspective on Compound AI Threats and Countermeasurescited by 1
- 2025SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Modelscited by 1
- 2025FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Modelscited by 1
- 2025FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement Learningcited by 1
- 2023Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferentcited by 0
- 2024RMF: A Risk Measurement Framework for Machine Learning Modelscited by 0
- 2025Remote Rowhammer Attack using Adversarial Observations on Federated Learning Clientscited by 0
- 2025FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement Learning10 Dec 2025
- 2025FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models28 Oct 2025
- 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
- 2025On the Relationship Between Robustness and Expressivity of Graph Neural Networks18 Apr 2025
- 2025Verification of Bit-Flip Attacks against Quantized Neural Networks22 Feb 2025
- 2024GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs21 Nov 2024
- 2024SoK: A Systems Perspective on Compound AI Threats and Countermeasures20 Nov 2024
- 2024DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers30 Jul 2024
- 2024RMF: A Risk Measurement Framework for Machine Learning Models15 Jun 2024
- 2024DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks22 May 2024
7 more
- 2024Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems10 May 2024
- 2023Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent2 Nov 2023
- 2023LLM for SoC Security: A Paradigm Shift9 Oct 2023
- 2022TrojViT: Trojan Insertion in Vision Transformers27 Aug 2022
- 2021DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories8 Nov 2021
- 2021ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack1 Nov 2021
- 2021Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead4 Jan 2021
- 2022TrojViT: Trojan Insertion in Vision Transformerscited by 31
- 2022TrojViT: Trojan Insertion in Vision Transformers27 Aug 2022
- 2021DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memoriescited by 42
- 2021Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Aheadcited by 41
- 2023LLM for SoC Security: A Paradigm Shiftcited by 22
- 2024GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMscited by 10
- 2021ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attackcited by 3
- 2024DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networkscited by 3
- 2025On the Relationship Between Robustness and Expressivity of Graph Neural Networkscited by 3
- 2025Verification of Bit-Flip Attacks against Quantized Neural Networkscited by 2
- 2025BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Modelscited by 2
- 2024DeepBaR: Fault Backdoor Attack on Deep Neural Network Layerscited by 1
- 2024SoK: A Systems Perspective on Compound AI Threats and Countermeasurescited by 1
- 2025SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Modelscited by 1
12 most cited of 16 All 16 (JSON)
- 2025FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models28 Oct 2025
- 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
- 2025On the Relationship Between Robustness and Expressivity of Graph Neural Networks18 Apr 2025
- 2025Verification of Bit-Flip Attacks against Quantized Neural Networks22 Feb 2025
- 2024GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs21 Nov 2024
- 2024SoK: A Systems Perspective on Compound AI Threats and Countermeasures20 Nov 2024
- 2024DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers30 Jul 2024
- 2024RMF: A Risk Measurement Framework for Machine Learning Models15 Jun 2024
- 2024DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks22 May 2024
- 2023Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent2 Nov 2023
12 newest of 16 All 16 (JSON)