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

We introduce ABACuS, a new low-cost hardware-counter-based RowHammer mitigation technique that performance-, energy-, and area-efficiently scales with worsening RowHammer vulnerability. We observe that both benign workloads and RowHammer…

Deep regression models are used in a wide variety of safety-critical applications, but are vulnerable to backdoor attacks. Although many defenses have been proposed for classification models, they are ineffective as they do not consider the…

Implementing machine learning algorithms on Internet of things (IoT) devices has become essential for emerging applications, such as autonomous driving, environment monitoring. But the limitations of computation capability and energy…

Large language models (LLMs) are inherently vulnerable to unintended privacy breaches. Consequently, systematic red-teaming research is essential for developing robust defense mechanisms. However, current data extraction methods suffer from…

State-of-the-art deep neural networks (DNNs) have been proven to be vulnerable to adversarial manipulation and backdoor attacks. Backdoored models deviate from expected behavior on inputs with predefined triggers while retaining performance…

Since its inception, Rowhammer exploits have rapidly evolved into increasingly sophisticated threats compromising data integrity and the control flow integrity of victim processes. Nevertheless, it remains a challenge for an attacker to…

Diffusion-based image generation models, such as Stable Diffusion or DALL-E 2, are able to learn from given images and generate high-quality samples following the guidance from prompts. For instance, they can be used to create artistic…

We propose a new RowHammer mitigation mechanism, CoMeT, that prevents RowHammer bitflips with low area, performance, and energy costs in DRAM-based systems at very low RowHammer thresholds. The key idea of CoMeT is to use low-cost and…

A fundamental assumption in software security is that memory contents do not change unless there is a legitimate deliberate modification. Classical fault attacks show that this assumption does not hold if the attacker has physical access.…

Diffusion models (DMs) are regarded as one of the most advanced generative models today, yet recent studies suggest that they are vulnerable to backdoor attacks, which establish hidden associations between particular input patterns and…

Disaggregated memory leverages recent technology advances in high-density, byte-addressable non-volatile memory and high-performance interconnects to provide a large memory pool shared across multiple compute nodes. Due to higher memory…

As deep learning gains popularity, edge IoT devices have seen proliferating deployment of pre-trained Deep Neural Network (DNN) models. These DNNs represent valuable intellectual property and face significant confidentiality threats from…

This work investigates the reduction of phasor measurement unit (PMU) data through low-rank matrix approximations. To reconstruct a PMU data matrix from fewer measurements, we propose the framework of interpolatory matrix decompositions…

Widespread use of memory unsafe programming languages (e.g., C and C++) leaves many systems vulnerable to memory corruption attacks. A variety of defenses have been proposed to mitigate attacks that exploit memory errors to hijack the…

Compressed prompts aid instruction-tuned language models (LMs) in overcoming context window limitations and reducing computational costs. Existing methods, which primarily based on training embeddings, face various challenges associated…

Register Files (RFs) are the most frequently accessed memories in a microprocessor for fast and efficient computation and control logic. Segment registers and control registers are especially critical for maintaining the CPU mode of…

In cloud computing environments, multiple tenants are often co-located on the same multi-processor system. Thus, preventing information leakage between tenants is crucial. While the hypervisor enforces software isolation, shared hardware,…

Large language models (LLMs) are increasingly integrated into IT infrastructures, where they process user data according to predefined instructions. However, conventional LLMs remain vulnerable to prompt injection, where malicious users…

Physically Unclonable Functions (PUFs) have become an important and promising hardware primitive for device fingerprinting, device identification, or key storage. Intrinsic PUFs leverage components already found in existing devices, unlike…

Reliability has emerged as a key topic of interest for researchers around the world to detect and/or mitigate the side effects of decreasing transistor sizes, such as soft errors. Traditional solutions, like DMR and TMR, incur significant…