We present ReTA (Relative Timing Analysis), a differential timing analysis technique to verify the impact of an update on the execution time of embedded software. Timing analysis is computationally expensive and labor...
We present ReTA (Relative Timing Analysis), a differential timing analysis technique to verify the impact of an update on the execution time of embedded software. Timing analysis is computationally expensive and labor intensive. Software updates render repeating the analysis from scratch a waste of resources and time, because their impact is inherently confined. To determine this boundary, in ReTA we apply a slicing procedure that identifies all relevant code segments and a statement categorization that determines how to analyze each such line of code. We adapt a subset of ReTA for integration into aiT, an industrial timing analysis tool, and also develop a complete implementation in a tool called Delta. Based on staple benchmarks and realistic code updates from official repositories, we test the accuracy by analyzing the worst-case execution time (WCET) before and after an update, comparing the measures with the use of the unmodified aiT as well as real executions on embedded hardware. Delta returns WCET information that ranges from exactly the WCET of real hardware to 148% of the new version's measured WCET. With the same benchmarks, the unmodified aiT estimates are 112% and 149% of the actual executions; therefore, even when Delta is pessimistic, an industry-strength tool such as aiT cannot do better. Crucially, we also show that ReTA decreases aiT's analysis time by 45% and its memory consumption by 8.9%, whereas removing ReTA from Delta, effectively rendering it a regular timing analysis tool, increases its analysis time by 27%.
international graduate students encounter unique challenges that impede their academic and personal success. This paper introduces an AI-powered chatbot designed specifically for these students, utilizing advanced lan...
详细信息
Global financial crime activity is driving demand for machine learning solutions in fraud prevention. However, prevention systems are commonly serviced to financial institutions in isolation, and few provisions exist ...
详细信息
ISBN:
(纸本)9798350381641
Global financial crime activity is driving demand for machine learning solutions in fraud prevention. However, prevention systems are commonly serviced to financial institutions in isolation, and few provisions exist for data sharing due to fears of unintentional leaks and adversarial attacks. Collaborative learning advances in finance are rare, and it is hard to find real-world insights derived from privacy-preserving data processing systems. In this paper, we present a collaborative deep learning framework for fraud prevention, designed from a privacy standpoint, and awarded at the recent PETs Prize Challenges. We leverage latent embedded representations of varied-length transaction sequences, along with local differential privacy, in order to construct a data release mechanism which can securely inform externally hosted fraud and anomaly detection models. We assess our contribution on two distributed data sets donated by large payment networks, and demonstrate robustness to popular inference-time attacks, along with utility-privacy trade-offs analogous to published work in alternative application domains.
Many applications have deadline requirements for their data delivery, such as real-time video, multiplayer gaming, and cloud AR/VR. However, the current transport layers' APIs are too primitive to accomplish that....
详细信息
ISBN:
(纸本)9781665482349
Many applications have deadline requirements for their data delivery, such as real-time video, multiplayer gaming, and cloud AR/VR. However, the current transport layers' APIs are too primitive to accomplish that. Therefore, today's applications are forced to build their customized and complex deadline-aware data delivery mechanisms. In this work, we design Deadline-aware Transport Protocol (DTP) to provide deliver-before-deadline service over the wild Internet. To fulfill the diverse and sometimes conflicting requirements over the fluctuating network, we design the Active-Drop-at-Sender scheduler and adaptive redundancy. We build DTP by extending QUIC, and then develop two applications that utilize DTP. Extensive evaluations demonstrate that DTP is easy to use and can bring significant performance improvement (1.2x to 5x) compared to vanilla QUIC.
Human brains exhibit an exceptional ability to rapidly identify, learn and follow new sound patterns. In contrast, conventional machine learning approaches tend to be static and lack the capacity for continuous learni...
详细信息
Digital Twin (DT) is a system of systems in which the conversion of every component, dynamic, and firmware of a physical system into its digital equivalent takes place. Technological breakthroughs in the field of vehi...
详细信息
The proceedings contain 51 papers. The topics discussed include: a 16-bit floating-point near-SRAM architecture for low-power sparse matrix-vector multiplication;optimized quantum circuit implementation of payoff func...
ISBN:
(纸本)9798350325997
The proceedings contain 51 papers. The topics discussed include: a 16-bit floating-point near-SRAM architecture for low-power sparse matrix-vector multiplication;optimized quantum circuit implementation of payoff function;dynamic scheduling for event-driven embedded industrial applications;towards robust process design kits with a scalable DevOps quality assurance platform;a novel approach to extract embedded memory design parameter through irradiation test;synthesis of SFQ circuits with compound gates;frontiers in ai acceleration: from approximate computing to FeFET monolithic 3D integration;and on the reliability of RRAM-based neural networks.
Ensuring the reliability of critical industrial systems across various sectors is crucial. It is essential to detect deviations from regular behaviour to mitigate disruptions and preserve infrastructure integrity. How...
详细信息
ISBN:
(纸本)9798350359329;9798350359312
Ensuring the reliability of critical industrial systems across various sectors is crucial. It is essential to detect deviations from regular behaviour to mitigate disruptions and preserve infrastructure integrity. However, accurately labelling anomaly datasets is challenging due to their rarity and manual annotation subjectivity. The conventional approach of training separate models for each dataset entity further complicates model development. This paper presents a novel Multi-task Learning framework combining LSTM Autoencoder with temporal attention mechanism (MTL-LATAM) for effective time series anomaly detection. Multitask learning models improve adaptability and generalizability, leading to reduced runtime and compute power while supporting zero-shot evaluation. These models offer flexibility in detecting emerging anomalies. Additionally, we introduce a dynamic thresholding mechanism to incorporate temporal context for anomaly detection and provide visualizations of attention weights to enhance interpretability. The study compares MTL- LATAM, with other multi-task models, evaluates multi-task versus single-task models and assesses the performance of the proposed frame- work in zero-shot learning scenarios. The findings indicate MTL- LATAM's effectiveness across real-world and open-source datasets, achieving 95% and 97% task synergy. The results underscore the superior performance of multi-task models in zero-shot tasks compared to individual models trained exclusively on their respective datasets.
As the complexity of power systems and the challenges posed by uncertainty continue to evolve, identifying promising areas for further investigation becomes essential to improve decision-making processes and enhance t...
详细信息
To enhance maritime situational awareness, real-time segmentation of small or distant ships from optical monitoring footage, poses significant performance challenges, especially on embeddedsystems. Efficient processi...
详细信息
ISBN:
(数字)9798350372601
ISBN:
(纸本)9798350372618
To enhance maritime situational awareness, real-time segmentation of small or distant ships from optical monitoring footage, poses significant performance challenges, especially on embeddedsystems. Efficient processing of full-resolution images is essential for precise small ship segmentation. In this paper, we introduce a framework that combines an optimized version of ScatYOLOv8+CBAM with a custom batch-processed Slicing Aided Hyper Inference (SAHI). This approach is aimed at efficient and accurate small ship segmentation, deployed on embeddedsystems, and is validated using a real-world maritime dataset (ShipSG). With our optimized ScatYOLOv8+CBAM, we substantially improve inference efficiency with a 36% faster inference speed compared to its predecessor in the lightest model size, without compromising segmentation accuracy. Additionally, the integration of batch-processed SAHI, despite an increase in computation time, improves the accuracy of small ship segmentation up to 11%, allowing more effective utilization of full-resolution imagery without compromising the computational resources of embedded platforms. Our findings set a new benchmark for embedded maritime monitoring and pave the way for future research to optimize real-time high-resolution processing in resource-constrained environments.
暂无评论