Novel non-volatile memory (NVM) technologies offer high-speed and high-density data storage. In addition, they overcome the von Neumann bottleneck by enabling computing-in-memory (CIM). Various computer architectures have been proposed to integrate CIM blocks in their design, forming a mixed-signal system to combine the computational benefits of CIM with the robustness of conventional CMOS. Novel electronic design automation (EDA) tools are necessary to design and manufacture these so-called neuromorphic systems. Furthermore, EDA tools must consider the impact of security vulnerabilities, as hardware security attacks have increased in recent years. Existing information flow analysis (IFA) frameworks offer an automated tool-suite to uphold the confidentiality property for sensitive data during the design of hardware. However, currently available mixed-signal EDA tools are not capable of analyzing the information flow of neuromorphic systems. To illustrate the shortcomings, we develop information flow protocols for NVMs that can be easily integrated in the already existing tool-suites. We show the limitation of the state-of-the-art by analyzing the flow from sensitive signals through multiple memristive crossbar structures to potential untrusted components and outputs. Finally, we provide a thorough discussion of the merits and flaws of the mixed-signal IFA frameworks on neuromorphic systems.
相關內容
Internet of Things (IoT) devices are increasingly pervasive and essential components in enabling new applications and services. However, their widespread use also exposes them to exploitable vulnerabilities and flaws that can lead to significant losses. In this context, ensuring robust cybersecurity measures is essential to protect IoT devices from malicious attacks. However, the current solutions that provide flexible policy specifications and higher security levels for IoT devices are scarce. To address this gap, we introduce T800, a low-resource packet filter that utilizes machine learning (ML) algorithms to classify packets in IoT devices. We present a detailed performance benchmarking framework and demonstrate T800's effectiveness on the ESP32 system-on-chip microcontroller and ESP-IDF framework. Our evaluation shows that T800 is an efficient solution that increases device computational capacity by excluding unsolicited malicious traffic from the processing pipeline. Additionally, T800 is adaptable to different systems and provides a well-documented performance evaluation strategy for security ML-based mechanisms on ESP32-based IoT systems. Our research contributes to improving the cybersecurity of resource-constrained IoT devices and provides a scalable, efficient solution that can be used to enhance the security of IoT systems.
With the growing popularity of various mobile devices, user targeting has received a growing amount of attention, which aims at effectively and efficiently locating target users that are interested in specific services. Most pioneering works for user targeting tasks commonly perform similarity-based expansion with a few active users as seeds, suffering from the following major issues: the unavailability of seed users for newcoming services and the unfriendliness of black-box procedures towards marketers. In this paper, we design an Entity Graph Learning (EGL) system to provide explainable user targeting ability meanwhile applicable to addressing the cold-start issue. EGL System follows the hybrid online-offline architecture to satisfy the requirements of scalability and timeliness. Specifically, in the offline stage, the system focuses on the heavyweight entity graph construction and user entity preference learning, in which we propose a Three-stage Relation Mining Procedure (TRMP), breaking loose from the expensive seed users. At the online stage, the system offers the ability of user targeting in real-time based on the entity graph from the offline stage. Since the user targeting process is based on graph reasoning, the whole process is transparent and operation-friendly to marketers. Finally, extensive offline experiments and online A/B testing demonstrate the superior performance of the proposed EGL System.
Blockchain-based IoT systems can manage IoT devices and achieve a high level of data integrity, security, and provenance. However, incorporating existing consensus protocols in many IoT systems limits scalability and leads to high computational cost and consensus latency. In addition, location-centric characteristics of many IoT applications paired with limited storage and computing power of IoT devices bring about more limitations, primarily due to the location-agnostic designs in blockchains. We propose a hierarchical and location-aware consensus protocol (LH-Raft) for IoT-blockchain applications inspired by the original Raft protocol to address these limitations. The proposed LH-Raft protocol forms local consensus candidate groups based on nodes' reputation and distance to elect the leaders in each sub-layer blockchain. It utilizes a threshold signature scheme to reach global consensus and the local and global log replication to maintain consistency for blockchain transactions. To evaluate the performance of LH-Raft, we first conduct an extensive numerical analysis based on the proposed reputation mechanism and the candidate group formation model. We then compare the performance of LH-Raft against the classical Raft protocol from both theoretical and experimental perspectives. We evaluate the proposed threshold signature scheme using Hyperledger Ursa cryptography library to measure various consensus nodes' signing and verification time. Experimental results show that the proposed LH-Raft protocol is scalable for large IoT applications and significantly reduces the communication cost, consensus latency, and agreement time for consensus processing.
Recent years have seen a surge in the popularity of acoustics-enabled personal devices powered by machine learning. Yet, machine learning has proven to be vulnerable to adversarial examples. A large number of modern systems protect themselves against such attacks by targeting artificiality, i.e., they deploy mechanisms to detect the lack of human involvement in generating the adversarial examples. However, these defenses implicitly assume that humans are incapable of producing meaningful and targeted adversarial examples. In this paper, we show that this base assumption is wrong. In particular, we demonstrate that for tasks like speaker identification, a human is capable of producing analog adversarial examples directly with little cost and supervision: by simply speaking through a tube, an adversary reliably impersonates other speakers in eyes of ML models for speaker identification. Our findings extend to a range of other acoustic-biometric tasks such as liveness detection, bringing into question their use in security-critical settings in real life, such as phone banking.
Analog compute-in-memory (CIM) systems are promising for deep neural network (DNN) inference acceleration due to their energy efficiency and high throughput. However, as the use of DNNs expands, protecting user input privacy has become increasingly important. In this paper, we identify a potential security vulnerability wherein an adversary can reconstruct the user's private input data from a power side-channel attack, under proper data acquisition and pre-processing, even without knowledge of the DNN model. We further demonstrate a machine learning-based attack approach using a generative adversarial network (GAN) to enhance the data reconstruction. Our results show that the attack methodology is effective in reconstructing user inputs from analog CIM accelerator power leakage, even at large noise levels and after countermeasures are applied. Specifically, we demonstrate the efficacy of our approach on an example of U-Net inference chip for brain tumor detection, and show the original magnetic resonance imaging (MRI) medical images can be successfully reconstructed even at a noise-level of 20% standard deviation of the maximum power signal value. Our study highlights a potential security vulnerability in analog CIM accelerators and raises awareness of using GAN to breach user privacy in such systems.
Software developers often resort to Stack Overflow (SO) to fill their programming needs. Given the abundance of relevant posts, navigating them and comparing different solutions is tedious and time-consuming. Recent work has proposed to automatically summarize SO posts to concise text to facilitate the navigation of SO posts. However, these techniques rely only on information retrieval methods or heuristics for text summarization, which is insufficient to handle the ambiguity and sophistication of natural language. This paper presents a deep learning based framework called ASSORT for SO post summarization. ASSORT includes two complementary learning methods, ASSORT_S and ASSORT_{IS}, to address the lack of labeled training data for SO post summarization. ASSORT_S is designed to directly train a novel ensemble learning model with BERT embeddings and domainspecific features to account for the unique characteristics of SO posts. By contrast, ASSORT_{IS} is designed to reuse pre-trained models while addressing the domain shift challenge when no training data is present (i.e., zero-shot learning). Both ASSORT_S and ASSORT_{IS} outperform six existing techniques by at least 13% and 7% respectively in terms of the F1 score. Furthermore, a human study shows that participants significantly preferred summaries generated by ASSORT_S and ASSORT_{IS} over the best baseline, while the preference difference between ASSORT_S and ASSORT_{IS} was small.
Automatic pronunciation assessment is a major component of a computer-assisted pronunciation training system. To provide in-depth feedback, scoring pronunciation at various levels of granularity such as phoneme, word, and utterance, with diverse aspects such as accuracy, fluency, and completeness, is essential. However, existing multi-aspect multi-granularity methods simultaneously predict all aspects at all granularity levels; therefore, they have difficulty in capturing the linguistic hierarchy of phoneme, word, and utterance. This limitation further leads to neglecting intimate cross-aspect relations at the same linguistic unit. In this paper, we propose a Hierarchical Pronunciation Assessment with Multi-aspect Attention (HiPAMA) model, which hierarchically represents the granularity levels to directly capture their linguistic structures and introduces multi-aspect attention that reflects associations across aspects at the same level to create more connotative representations. By obtaining relational information from both the granularity- and aspect-side, HiPAMA can take full advantage of multi-task learning. Remarkable improvements in the experimental results on the speachocean762 datasets demonstrate the robustness of HiPAMA, particularly in the difficult-to-assess aspects.
When designing interventions in public health, development, and education, decision makers rely on social network data to target a small number of people, capitalizing on peer effects and social contagion to bring about the most welfare benefits to the population. Developing new methods that are privacy-preserving for network data collection and targeted interventions is critical for designing sustainable public health and development interventions on social networks. In a similar vein, social media platforms rely on network data and information from past diffusions to organize their ad campaign and improve the efficacy of targeted advertising. Ensuring that these network operations do not violate users' privacy is critical to the sustainability of social media platforms and their ad economies. We study privacy guarantees for influence maximization algorithms when the social network is unknown, and the inputs are samples of prior influence cascades that are collected at random. Building on recent results that address seeding with costly network information, our privacy-preserving algorithms introduce randomization in the collected data or the algorithm output, and can bound each node's (or group of nodes') privacy loss in deciding whether or not their data should be included in the algorithm input. We provide theoretical guarantees of the seeding performance with a limited sample size subject to differential privacy budgets in both central and local privacy regimes. Simulations on synthetic and empirical network datasets reveal the diminishing value of network information with decreasing privacy budget in both regimes.
Human-in-the-loop aims to train an accurate prediction model with minimum cost by integrating human knowledge and experience. Humans can provide training data for machine learning applications and directly accomplish some tasks that are hard for computers in the pipeline with the help of machine-based approaches. In this paper, we survey existing works on human-in-the-loop from a data perspective and classify them into three categories with a progressive relationship: (1) the work of improving model performance from data processing, (2) the work of improving model performance through interventional model training, and (3) the design of the system independent human-in-the-loop. Using the above categorization, we summarize major approaches in the field, along with their technical strengths/ weaknesses, we have simple classification and discussion in natural language processing, computer vision, and others. Besides, we provide some open challenges and opportunities. This survey intends to provide a high-level summarization for human-in-the-loop and motivates interested readers to consider approaches for designing effective human-in-the-loop solutions.
It has been a long time that computer architecture and systems are optimized to enable efficient execution of machine learning (ML) algorithms or models. Now, it is time to reconsider the relationship between ML and systems, and let ML transform the way that computer architecture and systems are designed. This embraces a twofold meaning: the improvement of designers' productivity, and the completion of the virtuous cycle. In this paper, we present a comprehensive review of work that applies ML for system design, which can be grouped into two major categories, ML-based modelling that involves predictions of performance metrics or some other criteria of interest, and ML-based design methodology that directly leverages ML as the design tool. For ML-based modelling, we discuss existing studies based on their target level of system, ranging from the circuit level to the architecture/system level. For ML-based design methodology, we follow a bottom-up path to review current work, with a scope of (micro-)architecture design (memory, branch prediction, NoC), coordination between architecture/system and workload (resource allocation and management, data center management, and security), compiler, and design automation. We further provide a future vision of opportunities and potential directions, and envision that applying ML for computer architecture and systems would thrive in the community.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191