Adaptive Security Support for Heterogeneous Memory on GPUs

Yuan, Shougang; Awad, Amro; Yudha, Ardhi Wiratama Baskara; Solihin, Yan; Zhou, Huiyang

doi:10.1109/hpca53966.2022.00024

Cited by 9 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An approach involves conducting crosslayer GPU reliability evaluations, combining high-energy neutron beam experiments, fault simulation campaigns, and application profiling to unveil and mitigate GPU vulnerabilities [13]. Security has also been a focal point, with designs aiming to reduce the attack surface through low-overhead secure GPU memory, leveraging value locality to minimize authentication metadata and optimize memory bandwidth usage [14] [15] [16]. Furthermore, the concept of utilizing GPUs in System-on-Chip (SOC) architectures for industrial applications has been explored, proposing additional hard-ware and software diversity to improve safety integrity [17].…”

Section: Background a Gpus In High-integrity Autonomous Systemsmentioning

confidence: 99%

XeroZerox: Analysis and Optimization of GPU Memory Management for High-Integrity Autonomous Systems

Calderón,

ALEJANDROCALDERON,

Nicolás

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Autonomous systems require high-performance processing capabilities, which demand the use of powerful accelerators such as GPUs. However, the use of GPUs in critical systems presents several challenges, since GPU programming models rely on explicit dynamic memory management. Traditionally, dynamic memory allocation in such systems is restricted to certain controlled scenarios, which require programs to be rewritten so that all the required memory is allocated at the beginning of the program and released at its end. However, many GPU applications do not follow this approach. Moreover, when dynamic memory allocation is used, it is critical to compute the exact amount of memory that will be used as well as to minimize it, to guarantee that it fits in the physical system memory. In this paper we present XeroZerox, an open-source tool that automatically converts the traditional dynamic memory allocations of GPU applications into allocations served from a centralized and optimally sized memory pool, which is managed in a way better suited for critical systems. XeroZerox allows legacy GPU applications to be used in a critical setup without rewriting them, minimizing at the same time their memory consumption and memory management runtime overhead.

show abstract

Section: Background a Gpus In High-integrity Autonomous Systemsmentioning

confidence: 99%

XeroZerox: Analysis and Optimization of GPU Memory Management for High-Integrity Autonomous Systems

Calderón,

ALEJANDROCALDERON,

Nicolás

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For GPUs, [42] and [25] provide a secure execution environment that is quite similar to GuardNN. They are not specific to neural networks and thus don't leverage their characteristics.…”

Section: Designing a Custom Teementioning

confidence: 99%

Seculator: A Fast and Secure Neural Processing Unit

Shrivastava¹,

Sarangi²

2022

Preprint

View full text Add to dashboard Cite

Securing deep neural networks (DNNs) is a problem of significant interest since an ML model incorporates high-quality intellectual property, features of data sets painstakingly collated by mechanical turks, and novel methods of training on large cluster computers. Sadly, attacks to extract model parameters are on the rise, and thus designers are being forced to create architectures for securing such models. State-of-the-art proposals in this field take the deterministic memory access patterns of such networks into cognizance (albeit partially), group a set of memory blocks into a tile, and maintain state at the level of tiles (to reduce storage space). For providing integrity guarantees (tamper avoidance), they don't propose any significant optimizations, and still maintain block-level state.We observe that it is possible to exploit the deterministic memory access patterns of DNNs even further, and maintain state information for only the current tile and current layer, which may comprise a large number of tiles. This reduces the storage space, reduces the number of memory accesses, increases performance, and simplifies the design without sacrificing any security guarantees. The key techniques in our proposed accelerator architecture, Seculator, are to encode memory access patterns to create a small HW-based tile version number generator for a given layer, and to store layer-level MACs. We completely eliminate the need for having a MAC cache and a tile version number store (as used in related work). We show that using intelligently-designed mathematical operations, these structures are not required. By reducing such overheads, we show a speedup of 16% over the closest competing work.

show abstract

“…These studies imply that there are vulnerabilities in modern CNN environments that should be addressed in the literature. In [24,25], the authors proposed a secure execution environment for GPUs. Because these techniques are not limited to neural networks, they do not utilize related properties.…”

Section: Related Workmentioning

confidence: 99%

Efficient Integrity-Tree Structure for Convolutional Neural Networks through Frequent Counter Overflow Prevention in Secure Memories

Kim

Lee

Hong

et al. 2022

Sensors

View full text Add to dashboard Cite

Advancements in convolutional neural network (CNN) have resulted in remarkable success in various computing fields. However, the need to protect data against external security attacks has become increasingly important because inference process in CNNs exploit sensitive data. Secure Memory is a hardware-based protection technique that can protect the sensitive data of CNNs. However, naively applying secure memory to a CNN application causes significant performance and energy overhead. Furthermore, ensuring secure memory becomes more difficult in environments that require area efficiency and low-power execution, such as the Internet of Things (IoT). In this paper, we investigated memory access patterns for CNN workloads and analyzed their effects on secure memory performance. According to our observations, most CNN workloads intensively write to narrow memory regions, which can cause a considerable number of counter overflows. On average, 87.6% of total writes occur in 6.8% of the allocated memory space; in the extreme case, 93.9% of total writes occur in 1.4% of the allocated memory space. Based on our observations, we propose an efficient integrity-tree structure called Countermark-tree that is suitable for CNN workloads. The proposed technique reduces overall energy consumption by 48%, shows a performance improvement of 11.2% compared to VAULT-128, and requires a similar integrity-tree size to VAULT-64, a state-of-the-art technique.

show abstract

Adaptive Security Support for Heterogeneous Memory on GPUs

Cited by 9 publications

References 23 publications

XeroZerox: Analysis and Optimization of GPU Memory Management for High-Integrity Autonomous Systems

XeroZerox: Analysis and Optimization of GPU Memory Management for High-Integrity Autonomous Systems

Seculator: A Fast and Secure Neural Processing Unit

Efficient Integrity-Tree Structure for Convolutional Neural Networks through Frequent Counter Overflow Prevention in Secure Memories

Contact Info

Product

Resources

About