Related papers: Scanclave: Verifying Application Runtime Integrity…
While large language models (LLMs) are powerful assistants in programming tasks, they may also produce malicious code. Testing LLM-generated code therefore poses significant risks to assessment infrastructure tasked with executing untrusted…
New trusted computing primitives such as Intel SGX have shown the feasibility of running user-level applications in enclaves on a commodity trusted processor without trusting a large OS. However, the OS can still compromise the integrity of…
Federated learning has emerged as a popular paradigm for collaboratively training a model from data distributed among a set of clients. This learning setting presents, among others, two unique challenges: how to protect privacy of the…
Sensitive computation often has to be performed in a trusted execution environment (TEE), which, in turn, requires tamper-proof hardware. If the computational fabric can be tampered with, we may no longer be able to trust the correctness of…
Benchmarks are important measures to evaluate safety and compliance of AI models at scale. However, they typically do not offer verifiable results and lack confidentiality for model IP and benchmark datasets. We propose Attestable Audits,…
Variations in High Performance Computing (HPC) system software configurations mean that applications are typically configured and built for specific HPC environments. Building applications can require a significant investment of time and…
High-assurance security systems require strong isolation from the untrusted world to protect the security-sensitive or privacy-sensitive data they process. Existing regulations impose that such systems must execute in a trustworthy…
The logic of many protocols relies on time measurements. However, in Trusted Execution Environments (TEEs) like Intel SGX, the time source is outside the Trusted Computing Base: a malicious system hosting the TEE can manipulate that TEE's…
LLM-integrated app systems extend the utility of Large Language Models (LLMs) with third-party apps that are invoked by a system LLM using interleaved planning and execution phases to answer user queries. These systems introduce new attack…
Confidential computing protects data in use within Trusted Execution Environments (TEEs), but current TEEs provide little support for secure communication between components. As a result, pipelines of independently developed and deployed…
Unauthorized data alteration has been a longstanding threat since the emergence of malware. System and application software can be reinstalled and hardware can be replaced, but user data is priceless in many cases. Especially in recent…
Edge computing promises to reshape the centralized nature of today's cloud-based applications by bringing computing resources, at least in part, closer to the user. Reasons include the increasing need for real-time (short-delay,…
In TrustZone-assisted TEEs, the trusted OS has unrestricted access to both secure and normal world memory. Unfortunately, this architectural limitation has opened an aisle of exploration for attackers, which have demonstrated how to…
Security and privacy concerns in computer systems have grown in importance with the ubiquity of connected devices. TEEs provide security guarantees based on cryptographic constructs built in hardware. Intel software guard extensions (SGX),…
The rapid development of Internet of Things (IoT) technology has led to growing concerns about data security and user privacy in the interactions within distributed systems. Decentralized Applications (DApps) in distributed systems consist…
Many applications require the immutable and consistent sharing of data across organizational boundaries. Because conventional datastores cannot provide this functionality, blockchains have been proposed as one possible solution. Yet public…
We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones…
Protection of data-in-use is a key priority, for which Trusted Execution Environment (TEE) technology has unarguably emerged as a, possibly the most, promising solution. Multiple server-side TEE offerings have been released over the years,…
Over the past few years, several research groups have introduced innovative hardware designs for Trusted Execution Environments (TEEs), aiming to secure applications against potentially compromised privileged software, including the kernel.…
MLaaS (Machine Learning as a Service) has become popular in the cloud computing domain, allowing users to leverage cloud resources for running private inference of ML models on their data. However, ensuring user input privacy and secure…