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

RRAM-based in-Memory Computing is an exciting road for implementing highly energy efficient neural networks. This vision is however challenged by RRAM variability, as the efficient implementation of in-memory computing does not allow error…

Recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks, including evasion and backdoor (poisoning) attacks. On the defense side, there have been intensive efforts on improving both empirical and…

DRAM-based memory is a critical factor that creates a bottleneck on the system performance since the processor speed largely outperforms the DRAM latency. In this thesis, we develop a low-cost mechanism, called ChargeCache, which enables…

Deep neural networks are vulnerable to so-called adversarial examples: inputs which are intentionally constructed to cause the model to make incorrect predictions or classifications. Adversarial examples are often visually indistinguishable…

Deep Neural Network (DNN) based classifiers have recently been used for the modulation classification of RF signals. These classifiers have shown impressive performance gains relative to conventional methods, however, they are vulnerable to…

The success of diffusion models has enabled effortless, high-quality image modifications that precisely align with users' intentions, thereby raising concerns about their potential misuse by malicious actors. Previous studies have attempted…

Early backdoor attacks against machine learning set off an arms race in attack and defence development. Defences have since appeared demonstrating some ability to detect backdoors in models or even remove them. These defences work by…

Machine learning (ML) models serve as powerful tools for threat detection and mitigation; however, they also introduce potential new risks. Adversarial input can exploit these models through standard interfaces, thus creating new attack…

Despite rapid advancements, machine learning, particularly deep learning, is hindered by the need for large amounts of labeled data to learn meaningful patterns without overfitting and immense demands for computation and storage, which…

Security and energy-efficiency are critical for computing applications in general and for edge applications in particular. Digital in-Memory Computing (IMC) in SRAM cells have widely been studied to accelerate inference tasks to maximize…

In this study, we introduce RePD, an innovative attack Retrieval-based Prompt Decomposition framework designed to mitigate the risk of jailbreak attacks on large language models (LLMs). Despite rigorous pretraining and finetuning focused on…

The security goals of cloud providers and users include memory confidentiality and integrity, which requires implementing Replay-Attack protection (RAP). RAP can be achieved using integrity trees or mutually authenticated channels.…

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

DRAM-based main memories have read operations that destroy the read data, and as a result, must buffer large amounts of data on each array access to keep chip costs low. Unfortunately, system-level trends such as increased memory contention…

A deep learning system typically suffers from a lack of reproducibility that is partially rooted in hardware or software implementation details. The irreproducibility leads to skepticism in deep learning technologies and it can hinder them…

The memory controller is in charge of managing DRAM maintenance operations (e.g., refresh, RowHammer protection, memory scrubbing) to reliably operate modern DRAM chips. Implementing new maintenance operations often necessitates…

A reconfigurable intelligent surface (RIS) is commonly made of low-cost passive and reflective meta-materials with excellent beam steering capabilities. It is applied to enhance wireless communication systems as a customizable signal…

We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in a cross-silo federated learning setting by relying on multiparty homomorphic encryption. RHODE preserves the…

Reversible data hiding (RDH) has been extensively studied in the field of information security. In our previous work [1], an explicit implementation approaching the rate-distortion bound of RDH has been proposed. However, there are two…

SRAM Processing-in-Memory (PIM) has emerged as the most promising implementation for high-performance PIM, delivering superior computing density, energy efficiency, and computational precision. However, the pursuit of higher performance…