Related papers: ImPress: Securing DRAM Against Data-Disturbance Er…

Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering…

Memory-safety violations are a prevalent cause of both reliability and security vulnerabilities in systems software written in unsafe languages like C/C++. Unfortunately, all the existing software-based solutions to this problem exhibit…

Collected and annotated datasets, which are obtained through extensive efforts, are effective for training Deep Neural Network (DNN) models. However, these datasets are susceptible to be misused by unauthorized users, resulting in…

Incremental learning aims to enable machine learning models to continuously acquire new knowledge given new classes, while maintaining the knowledge already learned for old classes. Saving a subset of training samples of previously seen…

Extended Asynchronous DRAM Refresh (eADR) proposed by Intel extends the persistence domain from the Non-Volatile Memory (NVM) to CPU caches and offers the persistence guarantee. Due to allowing lazy persistence and decreasing the amounts of…

Deep learning, as widely known, is vulnerable to adversarial samples. This paper focuses on the adversarial attack on autoencoders. Safety of the autoencoders (AEs) is important because they are widely used as a compression scheme for data…

This paper investigates hardware-based memory compression designs to increase the memory bandwidth. When lines are compressible, the hardware can store multiple lines in a single memory location, and retrieve all these lines in a single…

Diffusion models (DMs) are advanced deep learning models that achieved state-of-the-art capability on a wide range of generative tasks. However, recent studies have shown their vulnerability regarding backdoor attacks, in which backdoored…

In recent years, Rowhammer has attracted significant attention from academia and industry alike. This technique, first published in 2014, flips bits in memory by repeatedly accessing neighbouring memory locations. Since its discovery,…

Sparse deep learning has reduced computation significantly, but its irregular non-zero data distribution complicates the data flow and hinders data reuse, increasing on-chip SRAM access and thus power consumption of the chip. This paper…

Implicit Neural Representations (INRs) encode discrete signals in a continuous manner using neural networks, demonstrating significant value across various multimedia applications. However, the vulnerability of INRs presents a critical…

Remote Direct Memory Access (RDMA) is a technology that allows direct memory access from the memory of one computer into that of another without involving either one's operating system. This enables high-throughput, low-latency networking,…

Deep neural networks (DNNs) have been found to be vulnerable to backdoor attacks, raising security concerns about their deployment in mission-critical applications. While existing defense methods have demonstrated promising results, it is…

The initial location of data in DRAMs is determined and controlled by the 'address-mapping' and even modern memory controllers use a fixed and run-time-agnostic address mapping. On the other hand, the memory access pattern seen at the…

Adversarial EXEmples are carefully-perturbed programs tailored to evade machine learning Windows malware detectors, with an ongoing effort to develop robust models able to address detection effectiveness. However, even if robust models can…

Compute-in-memory (PIM) mitigates the memory wall by performing computation within memory, reducing data movement and improving energy efficiency. DRAM-based PIM is particularly attractive due to its high density, mature manufacturing…

The security of the Person Re-identification(ReID) model plays a decisive role in the application of ReID. However, deep neural networks have been shown to be vulnerable, and adding undetectable adversarial perturbations to clean images can…

Training-time defenses, known as adversarial training, incur high training costs and do not generalize to unseen attacks. Test-time defenses solve these issues but most existing test-time defenses require adapting the model weights,…

The purpose of this document is to study the security properties of the Silver Bullet algorithm against worst-case RowHammer attacks. We mathematically demonstrate that Silver Bullet, when properly configured and implemented in a DRAM chip,…

Resistive random access memory (RRAM) is very well known for its potential application in in-memory and neural computing. However, they often have different types of device-to-device and cycle-to-cycle variability. This makes it harder to…