A Systematization of Knowledge (SoK) is presented that unifies the taxonomy of vehicular attack surfaces, evaluates FL topologies, and maps adversarial threats such as poisoning and inference attacks.
Abstract
Modern vehicular networks face an expanding attack surface across internal Electronic Control Units (ECUs) and external Vehicle-to-Everything (V2X) communication. Federated Learning (FL) has emerged as a decentralized paradigm to deploy Intrusion Detection Systems (IDS) without compromising data privacy. However, the vehicular FL-IDS literature suffers from fragmented methodologies and unrealistic experimental setups. This paper presents a Systematization of Knowledge (SoK) that unifies the taxonomy of vehicular attack surfaces, evaluates FL topologies, and maps adversarial threats such as poisoning and inference attacks. By auditing over 60 publications, we identify recurring pitfalls: artificial IID data splits, reliance on trivial benchmarks, weak adversarial evaluation, and omission of real-time CAN constraints. Finally, we define a forward-looking research agenda and outline minimum benchmarking requirements necessary to transition vehicular FL-IDS from optimistic simulations to secure, real-world deployment.
The suggested DP-FAL model is a privacy-conserving, scalable, and robust intrusion prevention system that can be used real-time V2X conditions and has the potential to be deployed safely, reliably, and sustainably in next-generation transportation systems.
S. Sonker, V. K. Raina, B. B. Sagar et al.· Discover Computing· 0 citations
This review underscores the potential of FL to become a foundational technology in next-generation cybersecurity systems, enabling scalable and privacy-preserving threat mitigation across distributed infrastructures.
With the proliferation of Internet of Things (IoT), critical infrastructures such as smart cities, industrial automation, precision healthcare, and intelligent transportation have seen a significant shift in their security landscape. As these critical infrastructures are increasingly depending on OneM2M standards for interoperability and scalable service management, they are simultaneously presenting a larger and more structured attack surface. One of the most serious and realistic threats in such scenarios is black-box adversarial attacks, in which an attacker can compromise Machine Learning (ML) and Deep Learning (DL)-based intrusion detection systems (IDS) without having prior knowledge of the ML/DL model's architecture, parameters, and training data. To mitigate such a critical challenge, we propose a multi-stage framework specific to OneM2M-based IoT networks that can effectively counter transfer-based and query-based black-box adversarial attacks. Our framework's effectiveness will be tested on a dataset of 1.25 million labeled network flows collected from Azure IoT Hub-based IoT devices over a 10-day period. We will test the robustness of our framework against three adversarial attacks: FGSM with $\varepsilon=0.05$, PGD with 40 iterations and step size 0.01, and C&W with L2 optimization and 1,000 iterations. The proposed pipeline consists of four different mechanisms: (1) adversarial training with the use of mixed clean and adversarial samples, (2) traffic sanitization to minimize malicious and/or suspicious traffic flows before processing by the Common Service Entity (CSE), (3) the use of a black-box adversarial detector based on feature transformation, and (4) the use of an ensemble-based IDS to make use of the results of the Random Forest, XGBoost, MLP, and 1D-CNN-based IDSs via majority voting. The experimental results show that the proposed Ensemble + multi-defense configuration results in 98.1% accuracy, 98.3% TPR, and 1.7% FNR. Most notably, the proposed Ensemble + multi-defense configuration results in an ASR of 11.2%, which is down by 86% compared to the 82.3% ASR achieved by the baseline IDS. Notably, the proposed framework results in limited overheads in terms of RTT (increased by 8 ms), CPU (increased by 17%), and RAM (increased by 1.6 GB).
Hamza Jamiri, A. Zyane· International Conference on...· 0 citations
Federated Learning has become a practical approach for training intrusion detection models across distributed Internet of Things devices, but it remains exposed to poisoning attacks, non-IID data heterogeneity, and free-rider exploitation. This paper presents DT-Guard, a defense framework that leverages a server-side Digital Twin as a controlled testing environment for actively verifying client model behavior. Each submitted update is deployed in the Digital Twin and evaluated on synthetic challenge data through a four-layer pipeline that examines detection capability, backdoor resistance, parameter deviation, and cross-round stability. A complementary aggregation scheme called DT-Driven Performance Weighting compares client predictions against the current global model, exposing free-riders whose outputs are nearly indistinguishable from the global baseline. We validate DT-Guard on CIC-IoT-2023 under five poisoning strategies. DT-Guard generally outperforms nine existing defenses in accuracy, false positive rate, and contribution fairness.
H. Pham, Duy The Phan, Van-Hau Pham· IEEE International Conferenc...· 0 citations
As vehicular networks move toward 5G/6G edge intelligence, federated learning (FL) is widely promoted as a privacy-preserving way for vehicles and infrastructure to train shared models without exposing raw sensor data. Yet the updates clients transmit still leak enough information to identify who sent them, which threatens the anonymity that safety-critical V2X applications assume and adds to existing concerns over adversarial ML, model poisoning, and backdoor attacks. We study server-side client identity inference from transmitted weight deltas using inertial (IMU) measurements, evaluated on the UCI Human Activity Recognition (HAR) benchmark as an accessible proxy for the IMU streams produced onboard connected vehicles. Across five attack classifiers and five non-IID partitions, an honest-but-curious server recovers client identity with near-perfect accuracy (approximately 1.000) from undefended updates, confirming a concrete identifiability risk. We then quantify the privacy-utility trade-off of a lightweight clip-then-noise defense by sweeping Gaussian noise (sigma in {0.00, 0.05, 0.10, 0.20, 0.50, 1.00}) at fixed clipping (C=1.0), and report formal (epsilon, delta)-DP budgets through Renyi accounting. A practical region (sigma in [0.1, 0.2]) drives attack accuracy to near-random while costing under 5% relative FL accuracy. Ensemble FL supplies complementary structural privacy with a 1/K anonymity-set bound and no noise penalty. Results are supported by cryptographic (SHA-256) train/evaluation gradient disjointness, three seeds, and a count-normalized attacker-advantage metric. We position HAR explicitly as a proxy and discuss what validation on true vehicular telemetry would require.
Ali Akarma, Toqeer Ali Syed, Muhammad Khan et al.· 0 citations
The increased attack surface of the sixth generation (6G) network makes old security measures ineffective. In the current paper, the AI-based optimization framework is suggested, combining deep reinforcement learning (DRL) to respond to adaptive threat mitigation and federated learning (FL) to privacy-preserving anomaly detection on distributed 6G nodes. The caching algorithm of query fragment achieves a 34% computation overhead with no associated drop in detection faithfulness. When tested on a 6G Massive IoT dataset and O-RAN simulation, the framework has a 97.8% detection rate against DDoS attacks, data injection attacks, and adversarial evasion attacks. Compared to current AI-based intrusion detection systems, it reduces false positives by 42 percent and shortens response time by 58 percent. Findings affirm that next generation wireless infrastructures require adaptive, intelligent security.
Naga Naveena Chennupati· 2026 7th International Confe...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
