密码学与安全

Speculative execution enhances processor performance by predicting intermediate results and executing instructions based on these predictions. However, incorrect predictions can lead to security vulnerabilities, as speculative instructions…

Trusted Execution Environments (TEEs) allow the secure execution of code on remote systems without the need to trust their operators. They use static attestation as a central mechanism for establishing trust, allowing remote parties to…

In low-altitude wireless networks (LAWN), federated learning (FL) enables collaborative intelligence among unmanned aerial vehicles (UAVs) and integrated sensing and communication (ISAC) devices while keeping raw sensing data local. Due to…

Mobile messaging apps are a fundamental communication infrastructure, used by billions of people every day to share information, including sensitive data. Security and Privacy are thus critical concerns for such applications. Although the…

Mobile networks are essential for modern societies. The most recent generation of mobile networks will be even more ubiquitous than previous ones. Therefore, the security of these networks as part of the critical infrastructure with…

Network traffic classification using self-supervised pre-training models based on Masked Autoencoders (MAE) has demonstrated a huge potential. However, existing methods are confined to isolated byte-level reconstruction of individual flows,…

Encrypted traffic classification is a critical task for network security. While deep learning has advanced this field, the occlusion of payload semantics by encryption severely challenges standard modeling approaches. Most existing…

The fast pace of modern AI is rapidly transforming traditional industrial systems into vast, intelligent and potentially unmanned autonomous operational environments driven by AI-based solutions. These solutions leverage various forms of…

The major mobile platforms, Android and iOS, have introduced changes that restrict user tracking to improve user privacy, yet apps continue to covertly track users via device fingerprinting. We study the opportunity to improve this dynamic…

LLM-based chatbots in government services face critical security gaps. Multi-turn adversarial attacks achieve over 90% success against current defenses, and single-layer guardrails are bypassed with similar rates. We present CivicShield, a…

Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning. We introduce Trojan-Speak, an adversarial fine-tuning method that bypasses Anthropic's…

As Large Language Models (LLMs) and multi-agent AI systems are demonstrating increasing potential in cybersecurity operations, organizations, policymakers, model providers, and researchers in the AI and cybersecurity communities are…

Modern Large Language Model (LLM) systems are assembled from third-party artifacts such as pre-trained weights, fine-tuning adapters, datasets, dependency packages, and container images, fetched through automated pipelines. This speed comes…

By utilising their adaptive activation functions, Kolmogorov-Arnold Networks (KANs) can be applied in a novel way for the diverse machine learning tasks, including cyber threat detection. KANs substitute conventional linear weights with…

The large-scale adoption of Large Language Models (LLMs) forces a trade-off between operational cost (OpEx) and data privacy. Current routing frameworks reduce costs but ignore prompt sensitivity, exposing users and institutions to leakage…

Privacy techniques have been developed for data-driven systems, but systems with non-numeric data cannot use typical noise-adding techniques. Therefore, we develop a new mechanism for privatizing state trajectories of symbolic systems that…

Intrusion Detection System (IDS) is often calibrated to known attacks and generalizes poorly to unknown threats. This paper proposes GMA-SAWGAN-GP, a novel generative augmentation framework built on a Self-Attention-enhanced Wasserstein GAN…

Dataset condensation aims to synthesize compact yet informative datasets that retain the training efficacy of full-scale data, offering substantial gains in efficiency. Recent studies reveal that the condensation process can be vulnerable…

Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…

This technical report presents SkillTester, a tool for evaluating the utility and security of agent skills. Its evaluation framework combines paired baseline and with-skill execution conditions with a separate security probe suite. Grounded…