The number of Internet of Things (IoT) applications, especially latency-sensitive ones, have been significantly increased. So, Cloud computing, as one of the main enablers of the IoT that offers centralized services, cannot solely satisfy the requirements of IoT applications. Edge/Fog computing, as a distributed computing paradigm, processes, and stores IoT data at the edge of the network, offering low latency, reduced network traffic, and higher bandwidth. The Edge/Fog resources are often less powerful compared to Cloud, and IoT data is dispersed among many geo-distributed servers. Hence, Federated Learning (FL), which is a machine learning approach that enables multiple distributed servers to collaborate on building models without exchanging the raw data, is well-suited to Edge/Fog computing environments, where data privacy is of paramount importance. Besides, to manage different FL tasks on Edge/Fog computing environments, a lightweight resource management framework is required to manage different incoming FL tasks while does not incur significant overhead on the system. Accordingly, in this paper, we propose a lightweight FL framework, called FLight, to be deployed on a diverse range of devices, ranging from resource limited Edge/Fog devices to powerful Cloud servers. FLight is implemented based on the FogBus2 framework, which is a containerized distributed resource management framework. Moreover, FLight integrates both synchronous and asynchronous models of FL. Besides, we propose a lightweight heuristic-based worker selection algorithm to select a suitable set of available workers to participate in the training step to obtain higher training time efficiency. The obtained results demonstrate the efficiency of the FLight.
相關內容
RISC-V is an emerging technology, with applications ranging from embedded devices to high-performance servers. Therefore, more and more security-critical workloads will be conducted with code that is compiled for RISC-V. Well-known microarchitectural side-channel attacks against established platforms like x86 apply to RISC-V CPUs as well. As RISC-V does not mandate any hardware-based side-channel countermeasures, a piece of code compiled for a generic RISC-V CPU in a cloud server cannot make safe assumptions about the microarchitecture on which it is running. Existing tools for aiding software-level precautions by checking side-channel vulnerabilities on source code or x86 binaries are not compatible with RISC-V machine code. In this work, we study the requirements and goals of architecture-specific leakage analysis for RISC-V and illustrate how to achieve these goals with the help of fast and precise dynamic binary analysis. We implement all necessary building blocks for finding side-channel leakages on RISC-V, while relying on existing mature solutions when possible. Our leakage analysis builds upon the modular side-channel analysis framework Microwalk, that examines execution traces for leakage through secret-dependent memory accesses or branches. To provide suitable traces, we port the ARM dynamic binary instrumentation tool MAMBO to RISC-V. Our port named MAMBO-V can instrument arbitrary binaries which use the 64-bit general purpose instruction set. We evaluate our toolchain on several cryptographic libraries with RISC-V support and identify multiple exploitable leakages.
With ChatGPT as a representative, tons of companies have began to provide services based on large Transformers models. However, using such a service inevitably leak users' prompts to the model provider. Previous studies have studied secure inference for Transformer models using secure multiparty computation (MPC), where model parameters and clients' prompts are kept secret. Despite this, these frameworks are still limited in terms of model performance, efficiency, and deployment. To address these limitations, we propose framework PUMA to enable fast and secure Transformer model inference. Our framework designs high quality approximations for expensive functions such as GeLU and softmax, and significantly reduce the cost of secure inference while preserving the model performance. Additionally, we design secure Embedding and LayerNorm procedures that faithfully implement the desired functionality without undermining the Transformer architecture. PUMA is about $2\times$ faster than the state-of-the-art framework MPCFORMER(ICLR 2023) and has similar accuracy as plaintext models without fine-tuning (which the previous works failed to achieve). PUMA can even evaluate LLaMA-7B in around 5 minutes to generate 1 token. To our best knowledge, this is the first time that a model with such a parameter size is able to be evaluated under MPC. PUMA has been open-sourced in the Github repository of SecretFlow-SPU.
Passwords remain the most widely used form of user authentication, despite advancements in other methods. However, their limitations, such as susceptibility to attacks, especially weak passwords defined by human users, are well-documented. The existence of weak human-defined passwords has led to repeated password leaks from websites, many of which are of large scale. While such password leaks are unfortunate security incidents, they provide security researchers and practitioners with good opportunities to learn valuable insights from such leaked passwords, in order to identify ways to improve password policies and other security controls on passwords. Researchers have proposed different data visualisation techniques to help analyse leaked passwords. However, many approaches rely solely on frequency analysis, with limited exploration of distance-based graphs. This paper reports PassViz, a novel method that combines the edit distance with the t-SNE (t-distributed stochastic neighbour embedding) dimensionality reduction algorithm for visualising and analysing leaked passwords in a 2-D space. We implemented PassViz as an easy-to-use command-line tool for visualising large-scale password databases, and also as a graphical user interface (GUI) to support interactive visual analytics of small password databases. Using the "000webhost" leaked database as an example, we show how PassViz can be used to visually analyse different aspects of leaked passwords and to facilitate the discovery of previously unknown password patterns. Overall, our approach empowers researchers and practitioners to gain valuable insights and improve password security through effective data visualisation and analysis.
Answering numerical questions over hybrid contents from the given tables and text(TextTableQA) is a challenging task. Recently, Large Language Models (LLMs) have gained significant attention in the NLP community. With the emergence of large language models, In-Context Learning and Chain-of-Thought prompting have become two particularly popular research topics in this field. In this paper, we introduce a new prompting strategy called Hybrid prompt strategy and Retrieval of Thought for TextTableQA. Through In-Context Learning, we prompt the model to develop the ability of retrieval thinking when dealing with hybrid data. Our method achieves superior performance compared to the fully-supervised SOTA on the MultiHiertt dataset in the few-shot setting.
Recently, Self-Supervised Representation Learning (SSRL) has attracted much attention in the field of computer vision, speech, natural language processing (NLP), and recently, with other types of modalities, including time series from sensors. The popularity of self-supervised learning is driven by the fact that traditional models typically require a huge amount of well-annotated data for training. Acquiring annotated data can be a difficult and costly process. Self-supervised methods have been introduced to improve the efficiency of training data through discriminative pre-training of models using supervisory signals that have been freely obtained from the raw data. Unlike existing reviews of SSRL that have pre-dominately focused upon methods in the fields of CV or NLP for a single modality, we aim to provide the first comprehensive review of multimodal self-supervised learning methods for temporal data. To this end, we 1) provide a comprehensive categorization of existing SSRL methods, 2) introduce a generic pipeline by defining the key components of a SSRL framework, 3) compare existing models in terms of their objective function, network architecture and potential applications, and 4) review existing multimodal techniques in each category and various modalities. Finally, we present existing weaknesses and future opportunities. We believe our work develops a perspective on the requirements of SSRL in domains that utilise multimodal and/or temporal data
Graph neural networks (GNNs) have been a hot spot of recent research and are widely utilized in diverse applications. However, with the use of huger data and deeper models, an urgent demand is unsurprisingly made to accelerate GNNs for more efficient execution. In this paper, we provide a comprehensive survey on acceleration methods for GNNs from an algorithmic perspective. We first present a new taxonomy to classify existing acceleration methods into five categories. Based on the classification, we systematically discuss these methods and highlight their correlations. Next, we provide comparisons from aspects of the efficiency and characteristics of these methods. Finally, we suggest some promising prospects for future research.
Deep Learning has implemented a wide range of applications and has become increasingly popular in recent years. The goal of multimodal deep learning is to create models that can process and link information using various modalities. Despite the extensive development made for unimodal learning, it still cannot cover all the aspects of human learning. Multimodal learning helps to understand and analyze better when various senses are engaged in the processing of information. This paper focuses on multiple types of modalities, i.e., image, video, text, audio, body gestures, facial expressions, and physiological signals. Detailed analysis of past and current baseline approaches and an in-depth study of recent advancements in multimodal deep learning applications has been provided. A fine-grained taxonomy of various multimodal deep learning applications is proposed, elaborating on different applications in more depth. Architectures and datasets used in these applications are also discussed, along with their evaluation metrics. Last, main issues are highlighted separately for each domain along with their possible future research directions.
Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for the three popular data types, i.e., images, graphs and text.
Generative Adversarial Networks (GANs) have recently achieved impressive results for many real-world applications, and many GAN variants have emerged with improvements in sample quality and training stability. However, they have not been well visualized or understood. How does a GAN represent our visual world internally? What causes the artifacts in GAN results? How do architectural choices affect GAN learning? Answering such questions could enable us to develop new insights and better models. In this work, we present an analytic framework to visualize and understand GANs at the unit-, object-, and scene-level. We first identify a group of interpretable units that are closely related to object concepts using a segmentation-based network dissection method. Then, we quantify the causal effect of interpretable units by measuring the ability of interventions to control objects in the output. We examine the contextual relationship between these units and their surroundings by inserting the discovered object concepts into new images. We show several practical applications enabled by our framework, from comparing internal representations across different layers, models, and datasets, to improving GANs by locating and removing artifact-causing units, to interactively manipulating objects in a scene. We provide open source interpretation tools to help researchers and practitioners better understand their GAN models.
ASR (automatic speech recognition) systems like Siri, Alexa, Google Voice or Cortana has become quite popular recently. One of the key techniques enabling the practical use of such systems in people's daily life is deep learning. Though deep learning in computer vision is known to be vulnerable to adversarial perturbations, little is known whether such perturbations are still valid on the practical speech recognition. In this paper, we not only demonstrate such attacks can happen in reality, but also show that the attacks can be systematically conducted. To minimize users' attention, we choose to embed the voice commands into a song, called CommandSong. In this way, the song carrying the command can spread through radio, TV or even any media player installed in the portable devices like smartphones, potentially impacting millions of users in long distance. In particular, we overcome two major challenges: minimizing the revision of a song in the process of embedding commands, and letting the CommandSong spread through the air without losing the voice "command". Our evaluation demonstrates that we can craft random songs to "carry" any commands and the modify is extremely difficult to be noticed. Specially, the physical attack that we play the CommandSongs over the air and record them can success with 94 percentage.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191