Related papers: GATEBLEED: Exploiting On-Core Accelerator Power Ga…
Rapid progress in generative AI has given rise to Compound AI systems - pipelines comprised of multiple large language models (LLM), software tools and database systems. Compound AI systems are constructed on a layered traditional software…
The transient execution attack is a type of attack leveraging the vulnerability of modern CPU optimization technologies. New attacks surface rapidly. The side-channel is a key part of transient execution attacks to leak data. In this work,…
Deep learning is gaining importance in many applications. However, Neural Networks face several security and privacy threats. This is particularly significant in the scenario where Cloud infrastructures deploy a service with Neural Network…
We introduce LLA, an effective intellectual property (IP) protection scheme for generative AI models. LLA leverages the synergy between hardware and software to defend against various supply chain threats, including model theft, model…
Modern processors dynamically control their operating frequency to optimize resource utilization, maximize energy savings, and conform to system-defined constraints. If, during the execution of a software workload, the running average of…
To lower cost and increase the utilization of Cloud Field-Programmable Gate Arrays (FPGAs), researchers have recently been exploring the concept of multi-tenant FPGAs, where multiple independent users simultaneously share the same remote…
Transformers have become the backbone of many Machine Learning (ML) applications, including language translation, summarization, and computer vision. As these models are increasingly deployed in shared Graphics Processing Unit (GPU)…
Covert channel attacks represent a significant threat to system security, leveraging shared resources to clandestinely transmit information from highly secure systems, thereby violating the system's security policies. These attacks exploit…
The deep learning revolution has been enabled in large part by GPUs, and more recently accelerators, which make it possible to carry out computationally demanding training and inference in acceptable times. As the size of machine learning…
Intel has introduced a trusted computing technology, Intel Software Guard Extension (SGX), which provides an isolated and secure execution environment called enclave for a user program without trusting any privilege software (e.g., an…
Side-channel information leakage is a known limitation of SGX. Researchers have demonstrated that secret-dependent information can be extracted from enclave execution through page-fault access patterns. Consequently, various recent research…
As a practical privacy-preserving learning method, split learning has drawn much attention in academia and industry. However, its security is constantly being questioned since the intermediate results are shared during training and…
Side-channel risks of Intel's SGX have recently attracted great attention. Under the spotlight is the newly discovered page-fault attack, in which an OS-level adversary induces page faults to observe the page-level access patterns of a…
In this paper we provide an implementation, evaluation, and analysis of PowerHammer, a malware (bridgeware [1]) that uses power lines to exfiltrate data from air-gapped computers. In this case, a malicious code running on a compromised…
Analogously to classical computers, quantum processors exhibit side channels that may give attackers access to potentially proprietary algorithms. We identify and exploit a previously unexplored side channel in trapped-ion quantum…
This paper evaluates new security threats due to the processor frontend in modern Intel processors. The root causes of the security threats are the multiple paths in the processor frontend that the micro-operations can take: through the…
Recent Deep Learning (DL) advancements in solving complex real-world tasks have led to its widespread adoption in practical applications. However, this opportunity comes with significant underlying risks, as many of these models rely on…
Meltdown and Spectre exploit microarchitectural changes the CPU makes during transient out-of-order execution. Using side-channel techniques, these attacks enable leaking arbitrary data from memory. As state-of-the-art software mitigations…
On-device machine learning (ODML) enables powerful edge applications, but power consumption remains a key challenge for resource-constrained devices. To address this, developers often face a trade-off between model accuracy and power…
Timing channels are information flows, encoded in the relative timing of events, that bypass the system's protection mechanisms. Any microarchitectural state that depends on execution history and affects the rate of progress of later…