密码学与安全

While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can…

Fingerprinting Large Language Models (LLMs)is essential for provenance verification and model attribution. Existing fingerprinting methods are primarily evaluated after fine-tuning, where models have already acquired stable signatures from…

Recent years have witnessed a rapid development of mobile GUI agents powered by large language models (LLMs), which can autonomously execute diverse device-control tasks based on natural language instructions. The increasing accuracy of…

Large Language Model-based Multi-Agent Systems (LLM-MAS) have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable messages. This vulnerability stems from a fundamental gap: LLM…

In this work, we present MoCQ, a neuro-symbolic static analysis framework that leverages large language models (LLMs) to automatically generate vulnerability detection patterns. This approach combines the precision and scalability of…

The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a…

Security engineering, from security requirements engineering to the implementation of cryptographic protocols, is often supported by domain-specific languages (DSLs). Unfortunately, a lack of knowledge about these DSLs, such as which…

Recent booming development of Generative Artificial Intelligence (GenAI) has facilitated model commercialization to reinforce the model performance, including licensing or trading Deep Neural Network (DNN) models. However, DNN model trading…

IoT devices have become indispensable components of our lives, and the advancement of AI technologies will make them even more pervasive, increasing the vulnerability to malfunctions or cyberattacks and raising privacy concerns. Encryption…

Large Language Models (LLMs) are redefining offensive cybersecurity by allowing the generation of harmful machine code with minimal human intervention. While attackers take advantage of dark LLMs such as XXXGPT and WolfGPT to produce…

Smishing (SMS phishing) has become a serious cybersecurity threat, especially for elderly and cyber-unaware individuals, causing financial loss and undermining user trust. Although prior work has focused on detecting smishing at the level…

From production to consumption, ensuring food quality and traceability depends on reliable monitoring of environmental conditions across the supply chain. Ambient sensing devices can collect relevant data such as temperature and humidity,…

Fully homomorphic encryption (FHE) has recently attracted significant attention as both a cryptographic primitive and a systems challenge. Given the latest advances in accelerated computing, FHE presents a promising opportunity for…

Large language model (LLM) watermarking has emerged as a promising approach for detecting and attributing AI-generated text, yet its robustness to black-box spoofing remains insufficiently evaluated. Existing evaluation methods often demand…

Traditionally, industrial control systems (ICS) were designed without security in mind, prioritizing availability and real-time communication. As these systems increasingly become targets of powerful adversaries, security can no longer be…

The application of Machine Learning techniques in code generation is now a common practice for most developers. Tools such as ChatGPT from OpenAI leverage the natural language processing capabilities of Large Language Models to generate…

AI agents that pay for resources via the x402 protocol embed payment metadata - resource URLs, descriptions, and reason strings - in every HTTP payment request. This metadata is transmitted to the payment server and to the centralised…

SMS Phishing (also known as 'smishing') is a growing deceptive social engineering (SE) attack that leverages mobile SMS to conduct cybercrimes such as stealing sensitive information or spreading malware by tricking users into interacting…

Security operations in smart cities demand detection systems that balance accuracy with response time. While ensemble methods like Random Forest achieve high accuracy, their computational overhead impedes real-time forensic triage. We…

We consider threshold secret sharing schemes based on cellular automata (CA) that allows for anonymous reconstruction, meaning that the secret can be recovered only as a function of the shares, without knowing the participants' identities.…