Ahmed Hussain

Saeif Al-Hazbi, Ahmed Hussain, Savio Sciancalepore et al.

Radio Frequency Fingerprinting (RFF) techniques promise to authenticate wireless devices at the physical layer based on inherent hardware imperfections introduced during manufacturing. Such RF transmitter imperfections are reflected into over-the-air signals, allowing receivers to accurately identify the RF transmitting source. Recent advances in Machine Learning, particularly in Deep Learning (DL), have improved the ability of RFF systems to extract and learn complex features that make up the device-specific fingerprint. However, integrating DL techniques with RFF and operating the system in real-world scenarios presents numerous challenges, originating from the embedded systems and the DL research domains. This paper systematically identifies and analyzes the essential considerations and challenges encountered in the creation of DL-based RFF systems across their typical development life-cycle, which include (i) data collection and preprocessing, (ii) training, and finally, (iii) deployment. Our investigation provides a comprehensive overview of the current open problems that prevent real deployment of DL-based RFF systems while also discussing promising research opportunities to enhance the overall accuracy, robustness, and privacy of these systems.

Konstantinos Kalogiannis, Ahmed Mohamed Hussain, Panos Papadimitratos

Misbehavior detection in Vehicle-to-Everything (V2X) networks is a second line of defense against insider falsification attacks that cryptographic mechanisms alone cannot address. Existing learning-based Misbehavior Detection Schemes (MDSs) are supervised, requiring labeled attack samples at training time, thus failing to counter unseen falsification attacks. We present PAMPOS, a causal transformer-decoder trained on benign VeReMi++ trajectories to learn normal mobility patterns. At inference time, misbehavior is identified as a deviation from the model's next-step kinematic predictions using a top-K normalized anomaly scoring mechanism that localizes falsification to specific kinematic features, without requiring attack-labeled training data. We evaluate PAMPOS across all 19 attack types in VeReMi++ under rush-hour and afternoon scenarios, achieving Area Under the Curve (AUC) values of up to 0.98 and F1-scores of up to 0.95 for most attack categories.

Saeif Alhazbi, Ahmed Mohamed Hussain, Gabriele Oligeri et al.

As Large Language Models (LLMs) become increasingly integrated into many technological ecosystems across various domains and industries, identifying which model is deployed or being interacted with is critical for the security and trustworthiness of the systems. Current verification methods typically rely on analyzing the generated output to determine the source model. However, these techniques are susceptible to adversarial attacks, operate in a post-hoc manner, and may require access to the model weights to inject a verifiable fingerprint. In this paper, we propose a novel passive and non-invasive fingerprinting technique that operates in real-time and remains effective even under encrypted network traffic conditions. Our method leverages the intrinsic autoregressive generation nature of language models, which generate text one token at a time based on all previously generated tokens, creating a unique temporal pattern like a rhythm or heartbeat that persists even when the output is streamed over a network. We find that measuring the Inter-Token Times (ITTs)-time intervals between consecutive tokens-can identify different language models with high accuracy. We develop a Deep Learning (DL) pipeline to capture these timing patterns using network traffic analysis and evaluate it on 16 Small Language Models (SLMs) and 10 proprietary LLMs across different deployment scenarios, including local host machine (GPU/CPU), Local Area Network (LAN), Remote Network, and Virtual Private Network (VPN). The experimental results confirm that our proposed technique is effective and maintains high accuracy even when tested in different network conditions. This work opens a new avenue for model identification in real-world scenarios and contributes to more secure and trustworthy language model deployment.

Johan Wahréus, Ahmed Mohamed Hussain, Panos Papadimitratos

Numerous studies have investigated methods for jailbreaking Large Language Models (LLMs) to generate harmful content. Typically, these methods are evaluated using datasets of malicious prompts designed to bypass security policies established by LLM providers. However, the generally broad scope and open-ended nature of existing datasets can complicate the assessment of jailbreaking effectiveness, particularly in specific domains, notably cybersecurity. To address this issue, we present and publicly release CySecBench, a comprehensive dataset containing 12662 prompts specifically designed to evaluate jailbreaking techniques in the cybersecurity domain. The dataset is organized into 10 distinct attack-type categories, featuring close-ended prompts to enable a more consistent and accurate assessment of jailbreaking attempts. Furthermore, we detail our methodology for dataset generation and filtration, which can be adapted to create similar datasets in other domains. To demonstrate the utility of CySecBench, we propose and evaluate a jailbreaking approach based on prompt obfuscation. Our experimental results show that this method successfully elicits harmful content from commercial black-box LLMs, achieving Success Rates (SRs) of 65% with ChatGPT and 88% with Gemini; in contrast, Claude demonstrated greater resilience with a jailbreaking SR of 17%. Compared to existing benchmark approaches, our method shows superior performance, highlighting the value of domain-specific evaluation datasets for assessing LLM security measures. Moreover, when evaluated using prompts from a widely used dataset (i.e., AdvBench), it achieved an SR of 78.5%, higher than the state-of-the-art methods.

Ahmed Mohamed Hussain, Nada Abughanam, Panos Papadimitratos

The deployment of the Internet of Things (IoT) in smart cities and critical infrastructure has enhanced connectivity and real-time data exchange but introduced significant security challenges. While effective, cryptography can often be resource-intensive for small-footprint resource-constrained (i.e., IoT) devices. Radio Frequency Fingerprinting (RFF) offers a promising authentication alternative by using unique RF signal characteristics for device identification at the Physical (PHY)-layer, without resorting to cryptographic solutions. The challenge is two-fold: how to deploy such RFF in a large scale and for resource-constrained environments. Edge computing, processing data closer to its source, i.e., the wireless device, enables faster decision-making, reducing reliance on centralized cloud servers. Considering a modest edge device, we introduce two truly lightweight Edge AI-based RFF schemes tailored for resource-constrained devices. We implement two Deep Learning models, namely a Convolution Neural Network and a Transformer-Encoder, to extract complex features from the IQ samples, forming device-specific RF fingerprints. We convert the models to TensorFlow Lite and evaluate them on a Raspberry Pi, demonstrating the practicality of Edge deployment. Evaluations demonstrate the Transformer-Encoder outperforms the CNN in identifying unique transmitter features, achieving high accuracy (> 0.95) and ROC-AUC scores (> 0.90) while maintaining a compact model size of 73KB, appropriate for resource-constrained devices.

Salahuddin Salahuddin, Ahmed Hussain, Jussi Löppönen et al.

While Large Language Models (LLMs) demonstrate exceptional natural language capabilities, general-purpose models lack specialized domain knowledge for effective cybersecurity analysis. In this work, we investigate Domain-Adaptive Continuous Pretraining (DAP) as a methodology for enhancing cybersecurity understanding in pretrained LLMs while preserving general language capabilities. We systematically adapted three decoder-based architectures -- Llama-3.1-8B, DeepSeek-R1-Distill-Qwen-14B, and Llama-3.3-70B-Instruct -- using a curated 126-million-word cybersecurity corpus from standards, academic literature, and various other sources. Our approach employed constrained training parameters and distributed FSDP training to balance domain specialization with knowledge preservation. Evaluation across three cybersecurity benchmarks, namely, CTI-MCQ, CyberMetric, and SecEval, demonstrates consistent improvements post-adaptation. The Llama-3.3-70B-Ins-DAP model achieved state-of-the-art accuracies of 0.718, 0.933, and 0.864, respectively, outperforming specialized models, including Llama-Primus-Base. Notably, competitive performance was achieved using substantially smaller datasets (118.8 million versus 2.77 billion tokens), demonstrating efficient domain specialization viability. We establish that targeted continuous pretraining enables effective cybersecurity domain adaptation with computational feasibility, providing foundations for specialized AI assistants in threat analysis, vulnerability assessment, and security documentation while challenging prevailing assumptions about data requirements for LLM specialization.

Johan Wahréus, Ahmed Hussain, Panos Papadimitratos

Large Language Models (LLMs) have transformed task automation and content generation across various domains while incorporating safety filters to prevent misuse. We introduce a novel jailbreaking framework that employs distributed prompt processing combined with iterative refinements to bypass these safety measures, particularly in generating malicious code. Our architecture consists of four key modules: prompt segmentation, parallel processing, response aggregation, and LLM-based jury evaluation. Tested on 500 malicious prompts across 10 cybersecurity categories, the framework achieves a 73.2% Success Rate (SR) in generating malicious code. Notably, our comparative analysis reveals that traditional single-LLM judge evaluation overestimates SRs (93.8%) compared to our LLM jury system (73.2%), with manual verification confirming that single-judge assessments often accept incomplete implementations. Moreover, we demonstrate that our distributed architecture improves SRs by 12% over the non-distributed approach in an ablation study, highlighting both the effectiveness of distributed prompt processing and the importance of robust evaluation methodologies in assessing jailbreak attempts.

Hexu Li, Konstantinos Kalogiannis, Ahmed Mohamed Hussain et al.

Vehicle platooning, with vehicles traveling in close formation coordinated through Vehicle-to-Everything (V2X) communications, offers significant benefits in fuel efficiency and road utilization. However, it is vulnerable to sophisticated falsification attacks by authenticated insiders that can destabilize the formation and potentially cause catastrophic collisions. This paper addresses this challenge: misbehavior detection in vehicle platooning systems. We present AttentionGuard, a transformer-based framework for misbehavior detection that leverages the self-attention mechanism to identify anomalous patterns in mobility data. Our proposal employs a multi-head transformer-encoder to process sequential kinematic information, enabling effective differentiation between normal mobility patterns and falsification attacks across diverse platooning scenarios, including steady-state (no-maneuver) operation, join, and exit maneuvers. Our evaluation uses an extensive simulation dataset featuring various attack vectors (constant, gradual, and combined falsifications) and operational parameters (controller types, vehicle speeds, and attacker positions). Experimental results demonstrate that AttentionGuard achieves up to 0.95 F1-score in attack detection, with robust performance maintained during complex maneuvers. Notably, our system performs effectively with minimal latency (100ms decision intervals), making it suitable for real-time transportation safety applications. Comparative analysis reveals superior detection capabilities and establishes the transformer-encoder as a promising approach for securing Cooperative Intelligent Transport Systems (C-ITS) against sophisticated insider threats.

Ahmed Mohamed Hussain, Gabriele Oligeri, Thiemo Voigt

We present a new machine learning-based attack that exploits network patterns to detect the presence of smart IoT devices and running services in the WiFi radio spectrum. We perform an extensive measurement campaign of data collection, and we build up a model describing the traffic patterns characterizing three popular IoT smart home devices, i.e., Google Nest Mini, Amazon Echo, and Amazon Echo Dot. We prove that it is possible to detect and identify with overwhelming probability their presence and the services running by the aforementioned devices in a crowded WiFi scenario. This work proves that standard encryption techniques alone are not sufficient to protect the privacy of the end-user, since the network traffic itself exposes the presence of both the device and the associated service. While more work is required to prevent non-trusted third parties to detect and identify the user's devices, we introduce Eclipse, a technique to mitigate these types of attacks, which reshapes the traffic making the identification of the devices and the associated services similar to the random classification baseline.