Logo des Repositoriums

Auflistung nach Schlagwort "Intel SGX"

1 - 2 von 2
  • Konferenzbeitrag
    Benchmarking the Second Generation of Intel SGX for Machine Learning Workloads
    (BTW 2023, 2023) Lutsch, Adrian; Singh, Gagandeep; Mundt, Martin; Mogk, Ragnar; Binnig, Carsten
    For domains with high data privacy and protection demands, such as health care and finance, outsourcing machine learning tasks often requires additional security measures. Trusted Execution Environments like Intel SGX are a powerful tool to achieve this additional security. Until recently, Intel SGX incurred high performance costs, mainly because it was severely limited in terms of available memory and CPUs. With the second generation of SGX, Intel alleviates these problems. Therefore, we revisit previous use cases for ML secured by SGX and show initial results of a performance study for ML workloads on SGXv2.
  • Konferenzbeitrag
    Secure Remote Computation using Intel SGX
    (SICHERHEIT 2018, 2018) Übler, David; Götzfried, Johannes; Müller, Tilo
    In this paper, we leverage SGX to provide a secure remote computation framework to be used in a cloud scenario. Our framework consists of two parts, a local part running on the user's machine and a remote part which is executed within the provider's environment. Users can connect and authenticate themselves to the remote side, verify the integrity of a newly spawned loading enclave, and deploy confidential code to the provider's machine. While we are not the first using SGX in a cloud scenario, we provide a full implementation considering all practical pitfalls, e.g., we use Intel's Attestation Services to prove the integrity of the loading enclave to our users. We also take care of establishing a secure bidirectional channel between the target enclave and the client running on the user's machine to send code, commands, and data. The performance overhead of CPU-bound applications using our framework is below 10% compared to remote computation without using SGX.