Praveen Gauravaram

Zakia Zaman, Praveen Gauravaram, Mahbub Hassan et al.

The rapid proliferation of the Internet of Things has intensified demand for robust privacy-preserving machine learning mechanisms to safeguard sensitive data generated by large-scale, heterogeneous, and resource-constrained devices. Unlike centralized environments, IoT ecosystems are inherently decentralized, bandwidth-limited, and latency-sensitive, exposing privacy risks across sensing, communication, and distributed training pipelines. These characteristics render conventional anonymization and centralized protection strategies insufficient for practical deployments. This survey presents a comprehensive IoT-centric, cross-paradigm analysis of privacy-preserving machine learning. We introduce a structured taxonomy spanning perturbation-based mechanisms such as differential privacy, distributed paradigms such as federated learning, cryptographic approaches including homomorphic encryption and secure multiparty computation, and generative synthesis techniques based on generative adversarial networks. For each paradigm, we examine formal privacy guarantees, computational and communication complexity, scalability under heterogeneous device participation, and resilience against threats including membership inference, model inversion, gradient leakage, and adversarial manipulation. We further analyze deployment constraints in wireless IoT environments, highlighting trade-offs between privacy, communication overhead, model convergence, and system efficiency within next-generation mobile architectures. We also consolidate evaluation methodologies, summarize representative datasets and open-source frameworks, and identify open challenges including hybrid privacy integration, energy-aware learning, privacy-preserving large language models, and quantum-resilient machine learning.

Nazatul Haque Sultan, Yan Bo, Yansong Gao et al.

Federated Learning (FL) enables multiple users to collaboratively train a machine learning model without sharing raw data, making it suitable for privacy-sensitive applications. However, local model or weight updates can still leak sensitive information. Secure aggregation protocols mitigate this risk by ensuring that only the aggregated updates are revealed. Among these, single-setup protocols, where key generation and exchange occur only once, are the most efficient due to reduced communication and computation overhead. However, existing single-setup protocols often lack support for dynamic user participation and do not provide strong privacy guarantees such as forward and backward secrecy. \par In this paper, we present a novel secure aggregation protocol that requires only a single setup for the entire FL training. Our protocol supports dynamic user participation, tolerates dropouts, and achieves both forward and backward secrecy. It leverages lightweight symmetric homomorphic encryption with a key negation technique to mask updates efficiently, eliminating the need for user-to-user communication. To defend against model inconsistency attacks, we introduce a low-overhead verification mechanism using message authentication codes (MACs). We provide formal security proofs under both semi-honest and malicious adversarial models and implement a full prototype. Experimental results show that our protocol reduces user-side computation by up to $99\%$ compared to state-of-the-art protocols like e-SeaFL (ACSAC'24), while maintaining competitive model accuracy. These features make our protocol highly practical for real-world FL deployments, especially on resource-constrained devices.

Zhiyu Zhu, Zhibo Jin, Hongsheng Hu et al.

AI systems, in particular with deep learning techniques, have demonstrated superior performance for various real-world applications. Given the need for tailored optimization in specific scenarios, as well as the concerns related to the exploits of subsurface vulnerabilities, a more comprehensive and in-depth testing AI system becomes a pivotal topic. We have seen the emergence of testing tools in real-world applications that aim to expand testing capabilities. However, they often concentrate on ad-hoc tasks, rendering them unsuitable for simultaneously testing multiple aspects or components. Furthermore, trustworthiness issues arising from adversarial attacks and the challenge of interpreting deep learning models pose new challenges for developing more comprehensive and in-depth AI system testing tools. In this study, we design and implement a testing tool, \tool, to comprehensively and effectively evaluate AI systems. The tool extensively assesses multiple measurements towards adversarial robustness, model interpretability, and performs neuron analysis. The feasibility of the proposed testing tool is thoroughly validated across various modalities, including image classification, object detection, and text classification. Extensive experiments demonstrate that \tool is the state-of-the-art tool for a comprehensive assessment of the robustness and trustworthiness of AI systems. Our research sheds light on a general solution for AI systems testing landscape.

Yinhao Jiang, Ba Dung Le, Tanveer Zia et al.

The virtual dimension called `Cyberspace' built on internet technologies has served people's daily lives for decades. Now it offers advanced services and connected experiences with the developing pervasive computing technologies that digitise, collect, and analyse users' activity data. This changes how user information gets collected and impacts user privacy at traditional cyberspace gateways, including the devices carried by users for daily use. This work investigates the impacts and surveys privacy concerns caused by this data collection, namely identity tracking from browsing activities, user input data disclosure, data accessibility in mobile devices, security of delicate data transmission, privacy in participating sensing, and identity privacy in opportunistic networks. Each of the surveyed privacy concerns is discussed in a well-defined scope according to the impacts mentioned above. Existing countermeasures are also surveyed and discussed, which identifies corresponding research gaps. To complete the perspectives, three complex open problems, namely trajectory privacy, privacy in smart metering, and involuntary privacy leakage with ambient intelligence, are briefly discussed for future research directions before a succinct conclusion to our survey at the end.

Nickolaos Koroniotis, Nour Moustafa, Benjamin Turnbull et al.

The Internet of Things (IoT) paradigm has displayed tremendous growth in recent years, resulting in innovations like Industry 4.0 and smart environments that provide improvements to efficiency, management of assets and facilitate intelligent decision making. However, these benefits are offset by considerable cybersecurity concerns that arise due to inherent vulnerabilities, which hinder IoT-based systems' Confidentiality, Integrity, and Availability. Security vulnerabilities can be detected through the application of penetration testing, and specifically, a subset of the information-gathering stage, known as vulnerability identification. Yet, existing penetration testing solutions can not discover zero-day vulnerabilities from IoT environments, due to the diversity of generated data, hardware constraints, and environmental complexity. Thus, it is imperative to develop effective penetration testing solutions for the detection of vulnerabilities in smart IoT environments. In this paper, we propose a deep learning-based penetration testing framework, namely Long Short-Term Memory Recurrent Neural Network-Enabled Vulnerability Identification (LSTM-EVI). We utilize this framework through a novel cybersecurity-oriented testbed, which is a smart airport-based testbed comprised of both physical and virtual elements. The framework was evaluated using this testbed and on real-time data sources. Our results revealed that the proposed framework achieves about 99% detection accuracy for scanning attacks, outperforming other four peer techniques.

Ali Dorri, Salil S. Kanhere, Raja Jurdak et al.

BlockChain (BC) has attracted tremendous attention due to its immutable nature and the associated security and privacy benefits. BC has the potential to overcome security and privacy challenges of Internet of Things (IoT). However, BC is computationally expensive, has limited scalability and incurs significant bandwidth overheads and delays which are not suited to the IoT context. We propose a tiered Lightweight Scalable BC (LSB) that is optimized for IoT requirements. We explore LSB in a smart home setting as a representative example for broader IoT applications. Low resource devices in a smart home benefit from a centralized manager that establishes shared keys for communication and processes all incoming and outgoing requests. LSB achieves decentralization by forming an overlay network where high resource devices jointly manage a public BC that ensures end-to-end privacy and security. The overlay is organized as distinct clusters to reduce overheads and the cluster heads are responsible for managing the public BC. LSB incorporates several optimizations which include algorithms for lightweight consensus, distributed trust and throughput management. Qualitative arguments demonstrate that LSB is resilient to several security attacks. Extensive simulations show that LSB decreases packet overhead and delay and increases BC scalability compared to relevant baselines.