Related papers: GATEBLEED: Exploiting On-Core Accelerator Power Ga…
The proliferation of smart, connected, always listening devices have introduced significant privacy risks to users in a smart home environment. Beyond the notable risk of eavesdropping, intruders can adopt machine learning techniques to…
Microelectronic systems are widely used in many sensitive applications (e.g., manufacturing, energy, defense). These systems increasingly handle sensitive data (e.g., encryption key) and are vulnerable to diverse threats, such as, power…
Generative AI has unleashed the power of content generation and it has also unwittingly opened the pandora box of realistic deepfake causing a number of social hazards and harm to businesses and personal reputation. The investigation &…
Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum. Yet, in reality, these models are part of larger systems that include components for training data filtering, output monitoring,…
As quantum computing advances, quantum circuit simulators serve as critical tools to bridge the current gap caused by limited quantum hardware availability. These simulators are typically deployed on cloud platforms, where users submit…
In modern computer systems, user processes are isolated from each other by the operating system and the hardware. Additionally, in a cloud scenario it is crucial that the hypervisor isolates tenants from other tenants that are co-located on…
New hardware primitives such as Intel SGX secure a user-level process in presence of an untrusted or compromised OS. Such "enclaved execution" systems are vulnerable to several side-channels, one of which is the page fault channel. In this…
To address the risks of increasingly capable AI systems, we introduce a hardware-level off-switch that embeds thousands of independent "security blocks" in each AI accelerator. This massively redundant architecture is designed to prevent…
Generative Artificial Intelligence (GenAI) presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent…
The aggressive performance optimizations in modern microprocessors can result in security vulnerabilities. For example, timing-based attacks in processor caches can steal secret keys or break randomization. So far, finding cache-timing…
As artificial intelligence systems become increasingly powerful, they pose growing risks to international security, creating urgent coordination challenges that current governance approaches struggle to address without compromising…
The various benefits of multi-tenanting, such as higher device utilization and increased profit margin, intrigue the cloud field-programmable gate array (FPGA) servers to include multi-tenanting in their infrastructure. However, this…
Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train or infer with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud.…
CPUs provide isolation mechanisms like virtualization and privilege levels to protect software. Yet these focus on architectural isolation while typically overlooking microarchitectural side channels, exemplified by Meltdown and Foreshadow.…
As large language models (LLMs) advance, ensuring AI safety and alignment is paramount. One popular approach is prompt guards, lightweight mechanisms designed to filter malicious queries while being easy to implement and update. In this…
The dawn of Generative Artificial Intelligence (GAI), characterized by advanced models such as Generative Pre-trained Transformers (GPT) and other Large Language Models (LLMs), has been pivotal in reshaping the field of data analysis,…
AI Accelerator (AIA) are specialized hardware e.g., Tensor Processing Unit (TPU), that enable optimal and efficient execution of AI applications and on-device inference. The growing demand for AI applications has led to the widespread…
The proliferation of AI technology gives rise to a variety of security threats, which significantly compromise the confidentiality and integrity of AI models and applications. Existing software-based solutions mainly target one specific…
Covert channels are communication channels used by attackers to transmit information from a compromised system when the access control policy of the system does not allow doing so. Previous work has shown that CPU frequency scaling can be…
Dataset condensation aims to synthesize compact yet informative datasets that retain the training efficacy of full-scale data, offering substantial gains in efficiency. Recent studies reveal that the condensation process can be vulnerable…