RIDL: Rogue in-flight data load

S Van Schaik, A Milburn, S Österlund… - … IEEE Symposium on …, 2019 - ieeexplore.ieee.org
We present Rogue In-flight Data Load (RIDL), a new class of speculative unprivileged and
constrained attacks to leak arbitrary data across address spaces and privilege boundaries …

On DRAM rowhammer and the physics of insecurity

AJ Walker, S Lee, D Beery - IEEE Transactions on Electron …, 2021 - ieeexplore.ieee.org
The dynamic random access memory (DRAM) disturb known as rowhammer (RH) has come
to dominate the insecurity of computing systems worldwide. Several studies have …

A modern primer on processing in memory

O Mutlu, S Ghose, J Gómez-Luna… - … computing: from devices …, 2022 - Springer
Modern computing systems are overwhelmingly designed to move data to computation. This
design choice goes directly against at least three key trends in computing that cause …

TRRespass: Exploiting the many sides of target row refresh

P Frigo, E Vannacc, H Hassan… - … IEEE Symposium on …, 2020 - ieeexplore.ieee.org
After a plethora of high-profile RowHammer attacks, CPU and DRAM vendors scrambled to
deliver what was meant to be the definitive hardware solution against the RowHammer …

Tbt: Targeted neural network attack with bit trojan

AS Rakin, Z He, D Fan - … of the IEEE/CVF Conference on …, 2020 - openaccess.thecvf.com
Abstract Security of modern Deep Neural Networks (DNNs) is under severe scrutiny as the
deployment of these models become widespread in many intelligence-based applications …

Rowhammer: A retrospective

O Mutlu, JS Kim - … Transactions on Computer-Aided Design of …, 2019 - ieeexplore.ieee.org
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 …

A survey of bit-flip attacks on deep neural network and corresponding defense methods

C Qian, M Zhang, Y Nie, S Lu, H Cao - Electronics, 2023 - mdpi.com
As the machine learning-related technology has made great progress in recent years, deep
neural networks are widely used in many scenarios, including security-critical ones, which …

Rowpress: Amplifying read disturbance in modern dram chips

H Luo, A Olgun, AG Yağlıkçı, YC Tuğrul… - Proceedings of the 50th …, 2023 - dl.acm.org
Memory isolation is critical for system reliability, security, and safety. Unfortunately, read
disturbance can break memory isolation in modern DRAM chips. For example, RowHammer …

Deepsteal: Advanced model extractions leveraging efficient weight stealing in memories

AS Rakin, MHI Chowdhuryy, F Yao… - 2022 IEEE symposium …, 2022 - ieeexplore.ieee.org
Recent advancements in Deep Neural Networks (DNNs) have enabled widespread
deployment in multiple security-sensitive domains. The need for resource-intensive training …

Revisiting rowhammer: An experimental analysis of modern dram devices and mitigation techniques

JS Kim, M Patel, AG Yağlıkçı, H Hassan… - 2020 ACM/IEEE 47th …, 2020 - ieeexplore.ieee.org
RowHammer is a circuit-level DRAM vulnerability, first rigorously analyzed and introduced in
2014, where repeatedly accessing data in a DRAM row can cause bit flips in nearby rows …