The Internet-of-Vehicles (IoV) has gained significant attention from both academia and industry, driven by its potential to enhance road safety and traffic efficiency. To fully realize this potential, securing IoV communications is essential, where detecting malicious Basic Safety Messages (BSMs) is a key challenge. To this end, machine learning (ML) has been widely employed to design Misbehavior Detection Systems (MDSs) for identifying manipulated BSMs. However, the existing MDSs mainly focus on improving detection accuracy, with little attention given to time efficiency. As safety in IoV is time-sensitive, designing a time-efficient MDS is urgently necessary. In this work, we propose BatchMDS, a time-efficient MDS using Convolutional Neural Network (CNN) and data-to-image transformation. By processing multiple BSMs simultaneously rather than individually, BatchMDS significantly reduces detection latency. Furthermore, this work proposes a novel combination of a sliding window mechanism and a Learned Feature Cache (LFC) to eliminate redundant computation during continuous detection. This work conducts extensive simulation over the VeRiMe dataset that contains five attacks. The experimental results demonstrate the effectiveness of the proposed BatchMDS, improving time efficiency of all attacks by at least 50% while remaining remarkable detection accuracy (≥ 97%).

Federated Learning enables collaborative model training across multiple IoT devices while preserving data privacy. However, the trustworthiness of the aggregation server remains a critical security vulnerability, especially in IoT environments that rely on potentially untrusted servers. Existing secure aggregation schemes exhibit critical flaws: verification mechanisms and aggregation processes are decoupled, allowing a malicious server to generate valid verification tokens while returning incorrect aggregation results. This enables covert attacks where verification succeeds despite erroneous models, thereby seriously compromising system reliability. As a result, designing a privacy-preserving aggregation scheme that integrates verification with aggregation, while keeping both low computational and communication costs, remains a persistent challenge. To address this issue, we propose a lightweight verifiable secure aggregation based on functional encryption for federated learning on IoT devices (VFE). Our protocol cryptographically binds multi-client function encryption to identity-based aggregate signatures, thereby deeply integrating aggregation computation with verification.We further employ an efficient bilinear-pairing-based verification protocol that supports single-step verification, thereby eliminating auxiliary mechanisms and significantly reducing verification complexity. The security analysis and extensive testing demonstrate that the proposed VFE protocol achieves robust verifiable aggregation in federated learning, while simultaneously preserving client privacy and substantially reducing both computation and communication overhead, making it highly suitable for IoT deployments.

The widespread usage of Microsoft Windows has unfortunately led to a surge in malware, posing a serious threat to the security and privacy of millions of users. In response, the research community has mobilized, with numerous efforts dedicated to strengthening defenses against these threats. The primary goal of these techniques is to detect malicious software early, preventing attacks before any damage occurs. However, many of these methods either claim that packing has minimal impact on malware detection or fail to address the reliability of their approaches when applied to packed samples. Consequently, they are not capable of assisting victims in handling packed programs or recovering from the damages caused by untimely malware detection. To address these challenges, we proposeVisUnpac, a static analysis-based data visualization framework for bolstering attack prevention while aiding recovery post-attack by unveiling malware patterns and offering more detailed information including both malware class and family. Our method includes unpacking packed malware programs, calculating local similarity descriptors based on basic blocks, enhancing correlations between descriptors, and refining them by minimizing noises to obtain self-analysis descriptors. Moreover, we employ machine learning to learn the correlations of self-analysis descriptors through architectural learning for final classification. Our comprehensive evaluation ofVisUnpacbased on a freshly gathered dataset with over 27,106 samples confirms its capability in accurately classifying malware programs with a precision of 99.7%. Additionally,VisUnpacreveals that most antivirus products in VirusTotal can not handle packed samples properly or provide precise malware classification information. We also achieve over 97% space savings compared to existing data visualization based methods.

Basic Safety Messages (BSMs) exchanged among vehicles and roadside units through vehicular communications can significantly enhance road safety and improve traffic efficiency. Protecting the integrity of BSMs, which are transmitted wirelessly in plaintext, is critical for the proper operation of vehicular networks. As a result, various machine learning-based misbehavior detection systems have been proposed to identify corrupted BSMs. Recent studies have applied federated learning methods to further preserve user privacy while facilitating detection model updates. However, supervised federated learning cannot be directly applied since BSMs received by vehicles are unlabeled. In this paper, we propose a semi-supervised federated learning framework that enables the federated training process between vehicles and the server without transmitting any datasets. Our experimental results show that the performance of the proposed semi-supervised framework is very close to the centralized method, while preserving user privacy and reducing communication costs.

Despite continuous advancements in defense mechanisms, attackers often find ways to circumvent security measures. Windows operating systems, in particular, are vulnerable due to fewer restrictions on downloading software from unknown sources, facilitating the spread of malware. To address this challenge, researchers have focused on developing techniques to identify Windows malware, crucial for mitigating potential damage. Traditional approaches typically categorize threats into broad classes such as trojans or adware, often failing to capture the full spectrum of malicious behaviors exhibited by diverse malware variants. In response, we propose a novel approach to malware categorization that incorporates both the general malware family and subfamily for each sample. Our method leverages self-similarity techniques to extract local semantics and similarities within the blocks of malware binaries while preserving correlations between these blocks. We utilize a VGG11 model to capture these features, enabling accurate classification. Central to our approach is the conversion of malware binaries into self-similarity descriptors, facilitating space savings while capturing essential semantics within blocks. By focusing on local self-similarities and their geometric layouts across malware, our method effectively identifies repetitive patterns indicative of malware behavior. Our proof-of-concept implementation demonstrates the effectiveness of our framework, achieving an impressive average precision of 98.2% on a newly gathered dataset with over 25,000 samples. Moreover, our method offers significant space savings, outperforming recent research efforts by a factor of over 96. These results underscore the efficacy of incorporating self-similarities and correlations within blocks for robust malware classification, making our approach a promising solution for real-world malware detection and prevention.

With the widespread prevalence of smart devices, mobile crowdsensing (MCS) becomes a new trend to encourage mobile nodes to participate in cooperative data collection in various Internet of Things (IoT) applications. In location-dependent MCS, location information of mobile nodes are collected and analyzed by service provider to assist in task allocation. If the service provider is not fully trusted, mobile node's privacy is leaked and accessed by unauthorized parties. How to preserve privacy while maintaining task allocation accuracy and efficiency becomes challenging. To this end, we propose a learning-based mechanism that involves two parts: 1) privacy-preserving task release and task allocation; 2) accurate and efficient task allocation. In the first part, we design a location-based symmetric key generator, which enables two parties to self-generate a symmetric key without depending on fully trusted authorities. By utilizing this key generator and Proxy Re-encryption, we propose a privacy preserving protocol to protect location information in task release and task allocation. In the second part, we design a reinforcement learning based task allocation algorithm to optimize the winners selection, which obtains high accuracy and efficiency. The performance analysis reveals that our proposed mechanism achieves accurate and efficient task allocation while preserving privacy in location-dependent MCS.

Mobile crowdsensing enables collaborative data sensing between cloud server and mobile nodes. To participate in the sensing task, mobile nodes upload their locations to the centralized cloud for task allocation. However, revealing locations to an untrusted cloud results in privacy leakage, such as trajectories tracking and home address exposal, threatening the personal security. Obfuscation and cryptography based schemes are two main solutions to protect the location privacy. However, these schemes may either degrade the accuracy of task allocation or rely on some strong assumptions. Thus, how to protect location privacy without strong assumptions while remaining high accuracy in task allocation is challenging. In this paper, we propose a secure protocol for edge-assisted mobile crowdsensing, which removes the assumption that the cloud cannot collude with mobile nodes. Specifically, we deploy homomorphic encryption among service requestor, cloud server and edge nodes in a collaborative manner. Benefiting from the additive property of the cryptosystem, the cloud is able to securely calculate the mobile node’s travel distance while knowing nothing about the mobile mode’s location and task location. Based on the protocol, two types of location-dependent task allocation, travel distance based task allocation and spatial distribution based task allocation, can be implemented with location privacy preservation. Experimental results show the effectiveness of our work in task allocation. In addition, comprehensive privacy discussion indicates that the proposed protocol is secure from the collusion between cloud and mobile nodes, while preserving the task location and location privacy of mobile nodes.

Distributed learning is proposed as a promising technique to reduce heavy data transmissions in centralized machine learning. By allowing the participants training the model locally, raw data is unnecessarily uploaded to the centralized cloud server, reducing the risks of privacy leakage as well. However, the existing studies have shown that an adversary is able to derive the raw data by analyzing the obtained machine learning models. To tackle this challenge, the state-of-the-art solutions mainly depend on differential privacy and encryption techniques (e.g., homomorphic encryption). Whereas, differential privacy degrades data utility and leads to inaccurate learning, while encryption based approaches are not effective to all machine learning algorithms due to the limited operations and excessive computation cost. In this work, we propose a novel scheme to resolve the privacy issues from the anonymous authentication approach. Different from the two types of existing solutions, this approach is generalized to all machine learning algorithms without reducing data utility, while guaranteeing privacy preservation. In addition, it can be integrated with detection schemes against data poisoning attacks and free-rider attacks, being more practical for distributed learning. To this end, we first design a pairing-based certificateless signature scheme. Based on the signature scheme, we further propose an anonymous and efficient authentication protocol which supports dynamic batch verification. The proposed protocol guarantees the desired security properties while being computationally efficient. Formal security proof and analysis have been provided to demonstrate the achieved security properties, including confidentiality, anonymity, mutual authentication, unlinkability, unforgeability, forward security, backward security, and non-repudiation. In addition, the performance analysis reveals that our proposed protocol significantly reduces the time consumption in batch verification, achieving high computational efficiency.

As a popular scenario of mobile crowdsensing, edge computing assisted vehicular crowdsensing (EVCS) encourages vehicles to participate in sensing data with the equipped devices. Due to the vehicular mobility, vehicles may dynamically enter and leave the coverage area of an edge node, leading to recurrent task allocations that consume excessive communication and computational resources. How to avoid recurring recruitment in task allocation is challenging. In this paper, we propose an optimization framework to facilitate task allocation by utilizing the cooperation between edge nodes. The proposed framework avoids complicated recruitment procedures while maximizing the connection time between the recruited vehicles and the edge node. Due to the NP-hardness of the formulated optimization problem, we design a reinforcement learning based algorithm to solve the problem with high accuracy and efficiency. Simulation results show the effectiveness of our proposed framework.

With the advancement of Internet of Things (IoT) and computing paradigms, massive data are collected and processed to enhance intelligent applications. However, by deliberately sending some queries, an attacker may be able to derive the sensitive information of IoT data owners. To prevent privacy leakage during IoT data query, differential privacy (DP) hides private information by introducing noise to the query results. As DP introduces randomized noise that will affect query accuracy (data utility), the tradeoff between privacy preservation and data utility is a challenge. In this article, we first propose a novel optimization framework for single query to minimize the privacy cost, while satisfying both personalized DP and customized data utility. We design a reinforcement learning-based algorithm for single query optimization framework (SQOF_RL) to solve the optimization problem efficiently. Then, we propose a SQOF_RL and SVT-based batch query optimization mechanism (S2BQOM) to answer more queries privately. The performance evaluation shows that SQOF_RL and S2BQOM can effectively optimize single query and batch queries in terms of privacy cost, data utility, personalized privacy, and query satisfaction. Finally, the performance analysis reveals that our work can be applied to multiple linear/nonlinear query functions instead of one particular query function.

The cloud-based Internet-of-Things (IoT) has been applied to support ubiquitous data collection and centralized data processing among various applications. Equipped with powerful resources, a semi-trusted cloud is able to deduce private information by launching inference attack. Homomorphic Encryption (HE) has been proposed as an effective way to preserve privacy from inference attack while allowing certain computation over ciphertext. However, HE leads to longer latency due to additional communication and computation overheads. In this paper, we propose an optimization framework in privacy-preserving access control under cloud-fog computing systems. The optimization goal is to maximize the average user satisfaction in the system, where cost and latency serve as key metrics measuring user satisfaction. Due to the NP-hardness of the formulated problem, we propose a low-complexity suboptimal algorithm to solve it, where the access offloading decision making, user cooperation, and resource allocation are considered. Simulation results are presented to show the advantages of our proposed algorithm in terms of the average USI (User Satisfaction Index) and the number of users with zero USI.