Related papers: Devlore: Device Interrupt Protection for Confident…
The rapid advancement of cloud-native technologies has created an urgent need for security. Currently, confidential containers are increasingly deployed in multi-tenant environments. Existing confidential container designs mainly adopt a…
Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (on-premises) to safeguard private data and enable customization. However, vulnerabilities in local environments can lead to unauthorized…
To safeguard user data privacy, on-device inference has emerged as a prominent paradigm on mobile and Internet of Things (IoT) devices. This paradigm involves deploying a model provided by a third party on local devices to perform inference…
Vehicular ad hoc network (VANET) is an enabling technology in modern transportation systems for providing safety and valuable information, and yet vulnerable to a number of attacks from passive eavesdropping to active interfering. Intrusion…
Secure multi-party computation (MPC) facilitates privacy-preserving computation between multiple parties without leaking private information. While most secure deep learning techniques utilize MPC operations to achieve feasible…
We present an instrumenting compiler for enforcing data confidentiality in low-level applications (e.g. those written in C) in the presence of an active adversary. In our approach, the programmer marks secret data by writing lightweight…
Microcode is an abstraction layer used by modern x86 processors that interprets user-visible CISC instructions to hardware-internal RISC instructions. The capability to update x86 microcode enables a vendor to modify CPU behavior in-field,…
AI agents powered by large language models are increasingly deployed as cloud services that autonomously access sensitive data, invoke external tools, and interact with other agents. However, these agents run within a complex multi-party…
In the era of cloud computing and data-driven applications, it is crucial to protect sensitive information to maintain data privacy, ensuring truly reliable systems. As a result, preserving privacy in deep learning systems has become a…
Computer systems often provide hardware support for isolation mechanisms like privilege levels, virtual memory, or enclaved execution. Over the past years, several successful software-based side-channel attacks have been developed that…
AMD Secure Encrypted Virtualization technologies enable confidential computing by protecting virtual machines from highly privileged software such as hypervisors. In this work, we develop the first, comprehensive symbolic model of the…
Ciphertexts of an order-preserving encryption (OPE) scheme preserve the order of their corresponding plaintexts. However, OPEs are vulnerable to inference attacks that exploit this preserved order. At another end, differential privacy has…
The ever-increasing size of open-source Large Language Models (LLMs) renders local deployment impractical for individual users. Decentralized computing has emerged as a cost-effective solution, allowing individuals and small companies to…
This article presents block-wise image encryption for the vision transformer and its applications. Perceptual image encryption for deep learning enables us not only to protect the visual information of plain images but to also embed unique…
Cloud computing relies on secure and efficient virtualization. Software level security solutions compromise the performance of virtual machines (VMs), as a large amount of computational power would be utilized for running the security…
Network processing elements in virtual machines, also known as Network Function Virtualization (NFV) often face CPU bottlenecks at the virtualization interface. Even highly optimized paravirtual device interfaces fall short of the…
Modern stream-based monitors collect detailed statistics of the runtime behavior of the system under observation. If the system runs in a privacy-sensitive context, this poses the risk of disclosing sensitive information. Differential…
Gradient inversion attacks pose significant privacy threats to distributed training frameworks such as federated learning, enabling malicious parties to reconstruct sensitive local training data from gradient communications between clients…
Modern operating systems manage and abstract hardware resources, to ensure efficient execution of user workloads. The operating system must securely interface with often untrusted user code while relying on hardware that is assumed to be…
Cloud stacks must isolate application components, while permitting efficient data sharing between components deployed on the same physical host. Traditionally, the MMU enforces isolation and permits sharing at page granularity. MMU…