secureTF

Quoc, Do Le; Gregor, Franz; Arnautov, Sergei; Kunkel, Roland; Bhatotia, Pramod; Fetzer, Christof

doi:10.1145/3423211.3425687

Cited by 28 publications

(5 citation statements)

References 77 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We report the average results obtained from running each experiment five times. The implementation of our model is based on PyTorch [30], and the experiments are conducted on a Linux server equipped with an NVIDIA QUADRO RTX 5000 GPU with 16GB of memory. Metrics.…”

Section: Experiments Setupmentioning

confidence: 99%

Tensor‐based gated graph neural network for automatic vulnerability detection in source code

Yang,

Ruan,

Zhang

2023

Software Testing Verif & Rel

View full text Add to dashboard Cite

The rapid expansion of smart devices leads to the increasing demand for vulnerability detection in the cyber security field. Writing secure source codes is crucial to protect applications and software. Recent vulnerability detection methods are mainly using machine learning and deep learning. However, there are still some challenges, how to learn accurate source code semantic embedding at the function level, how to effectively perform vulnerability detection using the learned semantic embedding of source code and how to solve the overfitting problem of learning‐based models. In this paper, we consider codes as various graphs with node features and propose a tensor‐based gated graph neural network called TensorGNN to produce code embedding for function‐level vulnerability detection. First, we propose a high‐dimensional tensor for combining different code graph representations. Second, inspired by the work of tensor technology, we propose the TensorGNN model to produce accurate code representations using the graph tensor. We evaluate our model on 7 C and C++ large open‐source code corpus (e.g. SARD&NVD, Debian, SATE IV, FFmpeg, libpng&LibTiff, Wireshark and Github datasets), which contains 13 types of vulnerabilities. Our TensorGNN model improves on existing state‐of‐the‐art works by 10%–30% on average in terms of vulnerability detection accuracy and F1, while our TensorGNN model needs less training time and model parameters. Specifically, compared with other existing works, our model reduces 25–47 times of the number of parameters and decreases 3–10 times of training time. Results of evaluations show that TensorGNN has better performance while using fewer training parameters and less training time.

show abstract

Section: Experiments Setupmentioning

confidence: 99%

Tensor‐based gated graph neural network for automatic vulnerability detection in source code

Yang,

Ruan,

Zhang

2023

Software Testing Verif & Rel

View full text Add to dashboard Cite

show abstract

“…To demonstrate the advantage of Perun in allowing users to select the trade-off between security and performance, we compare the performance of different security levels provided by Perun and the pure SGX based system called SecureTF [34]. We run the model training using the following setups: (i) only CPU (Native); (ii) GPU (Native GPU ); (iii) Perun, IMA enabled (Perun+IMA); (iv) Perun, IMA and SGX enabled (Perun+IMA+SGX ); (v) Perun with GPU, IMA enabled (Perun+IMA+GPU ).…”

Section: Security and Performance Trade-offmentioning

confidence: 99%

“…In contrast to these systems, Perun supports legacy ML applications without changing their source code. SecureTF [34] is the most relevant work for Perun because it also uses SCONE. It supports inference and training computation, as well as distributed settings.…”

Section: Related Workmentioning

confidence: 99%

“…Trusted computing technologies [14] provide integrity guarantees to the OS, allowing ML computations to access hardware accelerators. Our evaluation shows that Perun achieves 0.96× of native performance execution on the GPU and a speedup of up to 1560× in training a real-world medical dataset compared to a pure TEE-based approach [34].…”

Section: Introductionmentioning

confidence: 97%

“…Recent works [37,33] demonstrated that cryptographic techniques, such as secure multi-party computation [56] and fully homomorphic encryption [15], incur a large performance overhead, which currently prevents their adoption for computing-intensive ML. Alternative approaches [42,34] adopted trusted execution environments (TEEs) [36] to build ML systems showing that TEEs offer orders of magnitude faster ML computation, at the cost of weaker security guarantees compared to pure cryptographic solutions. Specifically, the pure cryptographic solutions compute on encrypted data, while in TEE-based approaches, a trusted ML software processes the plaintext data in a CPU-established execution environment (called enclave), which is isolated from the untrusted operating system and administrator.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Perun: Confidential Multi-stakeholder Machine Learning Framework with Hardware Acceleration Support

Ozga

Quoc

Fetzer

2021

Data and Applications Security and Privacy XXXV

Self Cite

View full text Add to dashboard Cite

Confidential multi-stakeholder machine learning (ML) allows multiple parties to perform collaborative data analytics while not revealing their intellectual property, such as ML source code, model, or datasets. State-of-the-art solutions based on homomorphic encryption incur a large performance overhead. Hardware-based solutions, such as trusted execution environments (TEEs), significantly improve the performance in inference computations but still suffer from low performance in training computations, e.g., deep neural networks model training, because of limited availability of protected memory and lack of GPU support.To address this problem, we designed and implemented Perun, a framework for confidential multi-stakeholder machine learning that allows users to make a trade-off between security and performance. Perun executes ML training on hardware accelerators (e.g., GPU) while providing security guarantees using trusted computing technologies, such as trusted platform module and integrity measurement architecture. Less computeintensive workloads, such as inference, execute only inside TEE, thus at a lower trusted computing base. The evaluation shows that during the ML training on CIFAR-10 and real-world medical datasets, Perun achieved a 161× to 1560× speedup compared to a pure TEE-based approach.

show abstract