USENIX Security2018Top-tier venue
ACES: Automatic Compartments for Embedded Systems
Abraham A. Clements, Naif Saleh Almakhdhub, Saurabh Bagchi, Mathias Payer
Abstract
Securing the rapidly expanding Internet of Things (IoT) is critical. Many of these "things" are vulnerable baremetal embedded systems, where the application executes directly on hardware without an operating system. Unfortunately, the integrity of current systems may be compromised by a single vulnerability, as recently shown by Google's P0 team against Broadcom's WiFi SoC. We present ACES (Automatic Compartments for Embedded Systems), an LLVM-based compiler that automatically infers and enforces inter-component isolation on bare-metal systems, thus applying the principle of least privileges. ACES takes a developerspecified compartmentalization policy and then automatically creates an instrumented binary that isolates compartments at run-time, while handling the hardware limitations of bare-metal embedded devices. We demonstrate ACES' ability to implement arbitrary compartmentalization policies by implementing three policies and comparing the compartment isolation, run-time overhead, and memory overhead. Our results show that ACES compartments can have low run-time overheads (13% on our largest test application), while using 59% less Flash, and 84% less RAM than the Mbed µVisor-the current state-of-the-art compartmentalization technique for baremetal systems. ACES compartments protect the integrity of privileged data, provide control-flow integrity between compartments, and reduce exposure to ROP attacks by 94.3% compared to µVisor.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext e5ae356e-d26f-4933-8053-9167708a4337Cited by top-tier papers32
- RVFuzzer: Finding Input Validation Bugs in Robotic Vehicles through Control-Guided TestingTaegyu Kim, Chung Hwan Kim, Junghwan Rhee, Fan Fei et al.USENIX Security 2019 · 92 citations
- DynPTA: Combining Static and Dynamic Analysis for Practical Selective Data ProtectionTapti Palit, Jarin Firose Moon, Fabian Monrose, Michalis PolychronakisS&P 2021 · 48 citations
- uXOM: Efficient eXecute-Only Memory on ARM Cortex-MDonghyun Kwon, Jangseop Shin, Giyeol Kim, Byoungyoung Lee et al.USENIX Security 2019 · 40 citations
- M2MON: Building an MMIO-based Security Reference Monitor for Unmanned VehiclesArslan Khan, Hyungsub Kim, Byoungyoung Lee, Dongyan Xu et al.USENIX Security 2021 · 35 citations
- Demons in the Shared Kernel: Abstract Resource Attacks Against OS-level VirtualizationNanzi Yang, Wenbo Shen, Jinku Li, Yutian Yang et al.CCS 2021 · 32 citations
Builds on2
- Securing Real-Time Microcontroller Systems through Customized Memory View SwitchingChung Hwan Kim, Taegyu Kim, Hongjun Choi, Zhongshu Gu et al.NDSS 2018 · 127 citations
- Protecting Bare-Metal Embedded Systems with Privilege OverlaysAbraham A. Clements, Naif Saleh Almakhdhub, Khaled Saab, Prashast Srivastava et al.S&P 2017 · 122 citations
Related papers
- OPEC: operation-based security isolation for bare-metal embedded systemsXia Zhou, Jiaqi Li, Wenlong Zhang, Yajin Zhou et al.EuroSys 2022 · 18 citations
- EC: Embedded Systems Compartmentalization via Intra-Kernel IsolationArslan Khan, Dongyan Xu, Dave Jing TianS&P 2023
- Low-Cost Privilege Separation with Compile Time Compartmentalization for Embedded SystemsArslan Khan, Dongyan Xu, Dave Jing TianS&P 2023
- TZ-DATASHIELD: Automated Data Protection for Embedded Systems via Data-Flow-Based CompartmentalizationZelun Kong, Minkyung Park, Le Guan, Ning Zhang et al.NDSS 2025
- Hardening Hypervisors with OmbroEthan Johnson, Colin Pronovost, John CriswellUSENIX ATC 2022
