This paper presents a learning-based methodology for developing an optimal lane-changing control policy for a
Remote Controlled (RC) car using real-time sensor data. The RC car is equipped with sensors including GPS, IMU devices,
and a camera integrated in an Nvidia Jetson AGX Xavier board. By a novel Adaptive Dynamic Programming (ADP) algorithm, our RC car is capable of learning the optimal lane-changing strategies based on the real-time processed measurement from the sensors. The experimental outcomes show that our learning-based control algorithm can be effectively implemented, adapt to parameter changes, and complete the lane changing tasks in a short learning time with satisfactory performance.
more »
« less
Fast Falcon Signature Generation and Verification Using ARMv8 NEON Instructions
We present our speed records for Falcon signature generation and verification on ARMv8-A architecture. Our implementations are benchmarked on Apple M1 ‘Firestorm’, Raspberry Pi 4 Cortex-A72, and Jetson AGX Xavier. Our optimized signature generation is 2x slower, but signature verification is 3–3.9x faster than the state-of-the-art CRYSTALS-Dilithium implementation on the same platforms. Faster signature verification may be particularly useful for the client side on con-strained devices. Our Falcon implementation outperforms the previous work targeting Jetson AGX Xavier by the factors 1.48x for signing in falcon512 and falcon1024, 1.52x for verifying in falcon512, and 1.70x for verifying in falcon1024. We achieve improvement in Falcon signature generation by supporting a larger subset of possible parameter values for FFT-related functions and applying our compressed twiddle-factor table to reduce memory usage. We also demonstrate that the recently proposed signature scheme Hawk, sharing optimized functionality with Falcon, has 3.3x faster signature generation and 1.6–1.9x slower signature verification when implemented on the same ARMv8 processors as Falcon.
more »
« less
- Award ID(s):
- 1801512
- PAR ID:
- 10438497
- Editor(s):
- El Mrabet, N.; De Feo, L.; Duquesne, S.
- Date Published:
- Journal Name:
- 14th International Conference on Cryptology, AFRICACRYPT 2023
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Efficient and adaptive computer vision systems have been proposed to make computer vision tasks, such as image classification and object detection, optimized for embedded or mobile devices. These solutions, quite recent in their origin, focus on optimizing the model (a deep neural network, DNN) or the system by designing an adaptive system with approximation knobs. Despite several recent efforts, we show that existing solutions suffer from two major drawbacks. First , while mobile devices or systems-on-chips (SOCs) usually come with limited resources including battery power, most systems do not consider the energy consumption of the models during inference. Second , they do not consider the interplay between the three metrics of interest in their configurations, namely, latency, accuracy, and energy. In this work, we propose an efficient and adaptive video object detection system — Virtuoso , which is jointly optimized for accuracy, energy efficiency, and latency. Underlying Virtuoso is a multi-branch execution kernel that is capable of running at different operating points in the accuracy-energy-latency axes, and a lightweight runtime scheduler to select the best fit execution branch to satisfy the user requirement. We position this work as a first step in understanding the suitability of various object detection kernels on embedded boards in the accuracy-latency-energy axes, opening the door for further development in solutions customized to embedded systems and for benchmarking such solutions. Virtuoso is able to achieve up to 286 FPS on the NVIDIA Jetson AGX Xavier board, which is up to 45 times faster than the baseline EfficientDet D3 and 15 times faster than the baseline EfficientDet D0. In addition, we also observe up to 97.2% energy reduction using Virtuoso compared to the baseline YOLO (v3) — a widely used object detector designed for mobiles. To fairly compare with Virtuoso , we benchmark 15 state-of-the-art or widely used protocols, including Faster R-CNN (FRCNN) [NeurIPS’15], YOLO v3 [CVPR’16], SSD [ECCV’16], EfficientDet [CVPR’20], SELSA [ICCV’19], MEGA [CVPR’20], REPP [IROS’20], FastAdapt [EMDL’21], and our in-house adaptive variants of FRCNN+, YOLO+, SSD+, and EfficientDet+ (our variants have enhanced efficiency for mobiles). With this comprehensive benchmark, Virtuoso has shown superiority to all the above protocols, leading the accuracy frontier at every efficiency level on NVIDIA Jetson mobile GPUs. Specifically, Virtuoso has achieved an accuracy of 63.9%, which is more than 10% higher than some of the popular object detection models, FRCNN at 51.1%, and YOLO at 49.5%.more » « less
-
With the burgeoning of autonomous driving, the edgedeployed integrated CPU/GPU (iGPU) platform gains significant attention from both academia and industries. NVIDIA issues a series of Jetson iGPU platforms that perform well in terms of computation capability, power consumption, and mobile size. However, these iGPU platforms typically contain very limited physical memory, which could be the bottleneck of these autonomous driving and edge computing applications. Although the introduction of the Unified Memory (UM) model in GPU programming can reduce the memory footprint, the programming legacy of the UM model initializes data on the CPU side by default as the conventional copyand- execute model does, which causes significant latency of application execution. In this paper, we propose an enhanced unified memory management model (eUMM), which delivers a prefetch-enhanced data initialization method on the GPU side of the iGPU platform. We evaluate eUMM on the representative Jetson TX2 and Xavier AGX platforms and demonstrate that eUMM not only reduces the initialization latency significantly but also benefits the following kernel computation and the entire application execution latency.more » « less
-
more » « less
This work presents the first hardware realisation of the Syndrome-Decodingin-the-Head (SDitH) signature scheme, which is a candidate in the NIST PQC process for standardising post-quantum secure digital signature schemes. SDitH’s hardness is based on conservative code-based assumptions, and it uses the Multi-Party-Computation-in-the-Head (MPCitH) construction. This is the first hardware design of a code-based signature scheme based on traditional decoding problems and only the second for MPCitH constructions, after Picnic. This work presents optimised designs to achieve the best area efficiency, which we evaluate using the Time-Area Product (TAP) metric. This work also proposes a novel hardware architecture by dividing the signature generation algorithm into two phases, namely offline and online phases for optimising the overall clock cycle count. The hardware designs for key generation, signature generation, and signature verification are parameterised for all SDitH parameters, including the NIST security levels, both syndrome decoding base fields (GF256 and GF251), and thus conforms to the SDitH specifications. The hardware design further supports secret share splitting, and the hypercube optimisation which can be applied in this and multiple other NIST PQC candidates. The results of this work result in a hardware design with a drastic reducing in clock cycles compared to the optimised AVX2 software implementation, in the range of 2-4x for most operations. Our key generation outperforms software drastically, giving a 11-17x reduction in runtime, despite the significantly faster clock speed. On Artix 7 FPGAs we can perform key generation in 55.1 Kcycles, signature generation in 6.7 Mcycles, and signature verification in 8.6 Mcycles for NIST L1 parameters, which increase for GF251, and for L3 and L5 parameters.
-
Authentication and integrity are fundamental security services that are critical for any viable system. However, some of the emerging systems (e.g., smart grids, aerial drones) are delay-sensitive, and therefore their safe and reliable operation requires delay-aware authentication mechanisms. Unfortunately, the current state-of-the-art authentication mechanisms either incur heavy computations or lack scalability for such large and distributed systems. Hence, there is a crucial need for digital signature schemes that can satisfy the requirements of delay-aware applications. In this paper, we propose a new digital signature scheme that we refer to as Compact Energy and Delay-aware Authentication (CEDA). In CEDA, signature generation and verification only require a small-constant number of multiplications and Pseudo Random Function (PRF) calls. Therefore, it achieves the lowest end-to-end delay among its counterparts. Our implementation results on an ARM processor and commodity hardware show that CEDA has the most efficient signature generation on both platforms, while offering a fast signature verification. Among its delay-aware counter-parts, CEDA has a smaller private key with a constant-size signature. All these advantages are achieved with the cost of a larger public key. This is a highly favorable trade-0ff for applications wherein the verffier is not memory-limited. We open-sourced our implementation of CEDA to enable its broad testing and adaptation.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1007/978-3-031-37679-5_18
