The use of Intel® Software Guard Extensions (SGX) offers robust security measures for shielding applications in untrusted environments. However, the performance overhead experienced by IO-intensive applications within SGX limits widespread adoption. Prior approaches have proposed the use of userspace kernel-bypass libraries such as Data Plane Development Kit (DPDK) inside SGX enclaves to enable direct access to IO devices. However, these solutions often come at the cost of increasing the Trusted Computing Base (TCB) size, expanding the attack surface, and complicating deployment. In this paper, we introduce Rakis, a comprehensive system that securely enables SGX enclave programs to leverage fast IO Linux kernel primitives without modifying user applications. Rakis prioritizes the security of its TCB components by employing rigorous software testing and verification methods, embodying a security-by-design approach. Importantly, Rakis achieves performance advantages without sacrificing TCB size or introducing deployment intricacies and demonstrates significant improvements in benchmark tests with a 4.6x increase in UDP network throughput compared to state-of-the-art SGX enclave LibOS (Gramine-SGX). To demonstrate the practical applicability of Rakis, we evaluate its performance on four real-world programs showcasing an average performance improvement of 2.8x compared to Gramine-SGX across all workloads.

Unit testing improves software quality by evaluating isolated sections of the program. This approach alleviates the need for comprehensive program-wide testing and confines the potential error scope within the software. However, unit test development is time-consuming, requiring developers to create appropriate test contexts and determine input values to cover different code regions. This problem is particularly pronounced in Rust due to its intricate type system, making traditional unit test generation tools ineffective in Rust projects. Recently, large language models (LLMs) have demonstrated their proficiency in understanding programming language and completing software engineering tasks. However, merely prompting LLMs with a basic prompt like “generate unit test for the following source code” often results in code with compilation errors. In addition, LLM-generated unit tests often have limited test coverage. To bridge this gap and harness the capabilities of LLM, we design and implement RUG, an end-to-end solution to automatically generate the unit test for Rust projects. To help LLM's generated test pass Rust strict compilation checks, RUG designs a semantic-aware bottom-up approach to divide the context construction problem into dependent sub-problems. It solves these sub-problems sequentially using an LLM and merges them to a complete context. To increase test coverage, RUG integrates coverage-guided fuzzing with LLM to prepare fuzzing harnesses. Applying RUG on 17 real-world Rust programs (average$24,937 \text{LoC}$), we show that RUG can achieve a high code coverage, up to$\mathbf{7 1. 3 7 \%}$, closely comparable to human effort$(\mathbf{7 3. 1 8 \%})$. We submitted 113 unit tests generated by RUG covering the new code: 53 of them have been accepted, 17 rejected, and 43 are pending for review.

The increasing integration of diverse co-processors and peripherals within mobile Arm System-on-Chips (SoCs) presents significant challenges for secure and efficient device I/O. Existing approaches relying on memory encryption introduce substantial performance and power overheads, which are exacerbated by the need for real-time data processing and strict power efficiency requirements in mobile platforms. These issues hinder the wider adoption of Arm Confidential Compute Architecture (CCA), which aims to provide robust security guarantees. To address these challenges, we present Portal, a secure and efficient device I/O interface for Arm CCA on mobile Arm SoCs. Portal achieves secure I/O through strict memory isolation without the need for memory encryption. By leveraging the memory isolation mechanism in Arm CCA, Portal enforces hardware-level access control, ensuring that only designated Realm virtual machines and peripherals can access the Portal-protected plaintext memory regions. This design eliminates the overhead associated with encryption, supports dynamic peripheral integration, and maintains robust security guarantees. The evaluation results demonstrate that Portal incurs a minimal one-time overhead of 9.8%, while enhancing scalability and power efficiency, making it a pivotal solution for fostering the adoption of the upcoming Arm CCA in mobile and resource-constrained environments.

Abstract The precise perception of the surrounding environment in traffic scenes is an important part of an intelligent transportation system. The event camera could provide complementary information to traditional frame‐based cameras, such as high dynamic range, and high time resolution, in the perception of traffic targets. To improve the precision and reliability of perception as well as facilitate lots of RGB camera‐based studies introduced to event cameras directly, a refined registration method for event‐based cameras and RGB cameras on the basis of pixel‐level region segmentation is proposed, to provide a fusion method at pixel level. A total of eight sequences and a dataset containing 260 typical traffic scenes are contained in the experiment dataset, both selected from DSEC, a traffic event‐based dataset. The registered event image shows a better spatial consistency with RGB images visually. Compared to the baseline, the evaluation indicators, such as the performance of the contrast, the proportion of overlapping pixels, and average registration accuracy have been improved. In the traffic object segmentation task, the average boundary displacement error of our method has decreased and the max decline value has reached 79.665%, compared to the boundary displacement error between ground truth and baseline. These results indicate prospective applications in the perception of intelligent transportation systems combined with event and RGB cameras. The traffic dataset with pixel‐level semantic annotations will be provided soon.

Coverage-guided fuzzing is considered one of the most efficient bug-finding techniques, given its number of bugs reported. However, coverage tracing provided by existing software-based approaches, such as source instrumentation and dynamic binary translation, can incur large overhead. Hindered by the significantly lowered execution speed, it also becomes less beneficial to improve coverage feedback by incorporating additional execution states.