As the Internet of Things (IoT) continues to evolve, smartphones have become essential components of IoT systems. However, with the increasing amount of personal information stored on smartphones, user privacy is at risk of being compromised by malicious attackers. Although malware detection engines are commonly installed on smartphones against these attacks, attacks that can evade these defenses may still emerge. In this paper, we analyze the return values of system calls on Android smartphones and find two never-disclosed vulnerable return values that can leak fine-grained user behaviors. Based on this observation, we present EavesDroid, an application-embedded side-channel attack on Android smartphones that allows unprivileged attackers to accurately identify fine-grained user behaviors (e.g., viewing messages and playing videos) via on-screen operations. Our attack relies on the correlation between user behaviors and the return values associated with hardware and system resources. While this attack is challenging since these return values are susceptible to fluctuation and misalignment caused by many factors, we show that attackers can eavesdrop on fine-grained user behaviors using a CNN-GRU classification model that adopts min-max normalization and multiple return value fusion. Our experiments on different models and versions of Android smartphones demonstrate that EavesDroid can achieve 98% and 86% inference accuracy for 17 classes of user behaviors in the test set and real-world settings, highlighting the risk of our attack on user privacy. Finally, we recommend effective malware detection, carefully designed obfuscation methods, or restrictions on reading vulnerable return values to mitigate this attack.
相關內容
Generative AI is on the rise, enabling everyone to produce realistic content via publicly available interfaces. Especially for guided image generation, diffusion models are changing the creator economy by producing high quality low cost content. In parallel, artists are rising against unruly AI, since their artwork are leveraged, distributed, and dissimulated by large generative models. Our approach, My Art My Choice (MAMC), aims to empower content owners by protecting their copyrighted materials from being utilized by diffusion models in an adversarial fashion. MAMC learns to generate adversarially perturbed "protected" versions of images which can in turn "break" diffusion models. The perturbation amount is decided by the artist to balance distortion vs. protection of the content. MAMC is designed with a simple UNet-based generator, attacking black box diffusion models, combining several losses to create adversarial twins of the original artwork. We experiment on three datasets for various image-to-image tasks, with different user control values. Both protected image and diffusion output results are evaluated in visual, noise, structure, pixel, and generative spaces to validate our claims. We believe that MAMC is a crucial step for preserving ownership information for AI generated content in a flawless, based-on-need, and human-centric way.
The machine learning (ML) sees an increasing prevalence of being used in the internet-of-things enabled smart grid. However, the trustworthiness of ML is a severe issue that must be addressed to accommodate the trend of ML-based smart grid applications (MLsgAPPs). The adversarial distortion injected into the power signal will greatly affect the system's normal control and operation. Therefore, it is imperative to conduct vulnerability assessment for MLsgAPPs applied in the context of safety-critical power systems. In this paper, we provide a comprehensive review of the recent progress in designing attack and defense methods for MLsgAPPs. Unlike the traditional survey about ML security, this is the first review work about the security of MLsgAPPs that focuses on the characteristics of power systems. The survey is organized from the aspects of adversarial assumptions, targeted applications, evaluation metrics, defending approaches, physics-related constraints, and applied datasets. We also highlight future directions on this topic to encourage more researchers to conduct further research on adversarial attacks and defending approaches for MLsgAPPs.
With the emergence of Large Language Models (LLMs), there has been a significant improvement in the programming capabilities of models, attracting growing attention from researchers. We propose CodeApex, a bilingual benchmark dataset focusing on the programming comprehension and code generation abilities of LLMs. CodeApex comprises three types of multiple-choice questions: conceptual understanding, commonsense reasoning, and multi-hop reasoning, designed to evaluate LLMs on programming comprehension tasks. Additionally, CodeApex utilizes algorithmic questions and corresponding test cases to assess the code quality generated by LLMs. We evaluate 14 state-of-the-art LLMs, including both general-purpose and specialized models. GPT exhibits the best programming capabilities, achieving approximate accuracies of 50% and 56% on the two tasks, respectively. There is still significant room for improvement in programming tasks. We hope that CodeApex can serve as a reference for evaluating the coding capabilities of LLMs, further promoting their development and growth. Datasets are released at \url{//github.com/APEXLAB/CodeApex.git}. CodeApex submission website is \url{//apex.sjtu.edu.cn/codeapex/}.
The evolution of communication technologies, exemplified by the Internet of Things (IoT) and cloud computing, has significantly enhanced the speed and accessibility of Public Safety (PS) services, critical to ensuring the safety and security of our environment. However, these advancements also introduce inherent security and privacy challenges. In response, this research presents a novel and adaptable access control scheme tailored to PS services in cloud-supported IoT environments. Our proposed access control protocol leverages the strengths of Key Policy Attribute Based Encryption (KP-ABE) and Identity-Based Broadcast Encryption (IDBB), combining them to establish a robust security framework for cloud-supported IoT in the context of PS services. Through the implementation of an Elliptic Curve Diffie-Hellman (ECDH) scheme between entities, we ensure entity authentication, data confidentiality, and integrity, addressing fundamental security requirements. A noteworthy aspect of our lightweight protocol is the delegation of user private key generation within the KP-ABE scheme to an untrusted cloud entity. This strategic offloading of computational and communication overhead preserves data privacy, as the cloud is precluded from accessing sensitive information. To achieve this, we employ an IDBB scheme to generate secret private keys for system users based on their roles, requiring the logical conjunction ('AND') of user attributes to access data. This architecture effectively conceals user identities from the cloud service provider. Comprehensive analysis validates the efficacy of the proposed protocol, confirming its ability to ensure system security and availability within acceptable parameters.
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
Recommender system is one of the most important information services on today's Internet. Recently, graph neural networks have become the new state-of-the-art approach of recommender systems. In this survey, we conduct a comprehensive review of the literature in graph neural network-based recommender systems. We first introduce the background and the history of the development of both recommender systems and graph neural networks. For recommender systems, in general, there are four aspects for categorizing existing works: stage, scenario, objective, and application. For graph neural networks, the existing methods consist of two categories, spectral models and spatial ones. We then discuss the motivation of applying graph neural networks into recommender systems, mainly consisting of the high-order connectivity, the structural property of data, and the enhanced supervision signal. We then systematically analyze the challenges in graph construction, embedding propagation/aggregation, model optimization, and computation efficiency. Afterward and primarily, we provide a comprehensive overview of a multitude of existing works of graph neural network-based recommender systems, following the taxonomy above. Finally, we raise discussions on the open problems and promising future directions of this area. We summarize the representative papers along with their codes repositories in //github.com/tsinghua-fib-lab/GNN-Recommender-Systems.
Recommender systems have been widely applied in different real-life scenarios to help us find useful information. Recently, Reinforcement Learning (RL) based recommender systems have become an emerging research topic. It often surpasses traditional recommendation models even most deep learning-based methods, owing to its interactive nature and autonomous learning ability. Nevertheless, there are various challenges of RL when applying in recommender systems. Toward this end, we firstly provide a thorough overview, comparisons, and summarization of RL approaches for five typical recommendation scenarios, following three main categories of RL: value-function, policy search, and Actor-Critic. Then, we systematically analyze the challenges and relevant solutions on the basis of existing literature. Finally, under discussion for open issues of RL and its limitations of recommendation, we highlight some potential research directions in this field.
Dialogue systems are a popular Natural Language Processing (NLP) task as it is promising in real-life applications. It is also a complicated task since many NLP tasks deserving study are involved. As a result, a multitude of novel works on this task are carried out, and most of them are deep learning-based due to the outstanding performance. In this survey, we mainly focus on the deep learning-based dialogue systems. We comprehensively review state-of-the-art research outcomes in dialogue systems and analyze them from two angles: model type and system type. Specifically, from the angle of model type, we discuss the principles, characteristics, and applications of different models that are widely used in dialogue systems. This will help researchers acquaint these models and see how they are applied in state-of-the-art frameworks, which is rather helpful when designing a new dialogue system. From the angle of system type, we discuss task-oriented and open-domain dialogue systems as two streams of research, providing insight into the hot topics related. Furthermore, we comprehensively review the evaluation methods and datasets for dialogue systems to pave the way for future research. Finally, some possible research trends are identified based on the recent research outcomes. To the best of our knowledge, this survey is the most comprehensive and up-to-date one at present in the area of dialogue systems and dialogue-related tasks, extensively covering the popular frameworks, topics, and datasets.
This paper surveys the field of transfer learning in the problem setting of Reinforcement Learning (RL). RL has been the key solution to sequential decision-making problems. Along with the fast advance of RL in various domains. including robotics and game-playing, transfer learning arises as an important technique to assist RL by leveraging and transferring external expertise to boost the learning process. In this survey, we review the central issues of transfer learning in the RL domain, providing a systematic categorization of its state-of-the-art techniques. We analyze their goals, methodologies, applications, and the RL frameworks under which these transfer learning techniques would be approachable. We discuss the relationship between transfer learning and other relevant topics from an RL perspective and also explore the potential challenges as well as future development directions for transfer learning in RL.
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
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191