密码学与安全
In recent years, numerous incidents involving the leakage of website accounts and text passwords (referred to as passwords) have raised significant concerns regarding the potential exposure of personal information. These events underscore…
The widespread adoption of Large Language Models (LLMs) in critical applications has introduced severe reliability and security risks, as LLMs remain vulnerable to notorious threats such as hallucinations, jailbreak attacks, and backdoor…
Data redundancy techniques have been tested in several different applications to provide fault tolerance and performance gains. The use of these techniques is mostly seen at the hardware, device driver, or file system level. In practice,…
In an increasingly interconnected world, Cyber-Physical Systems (CPS) are essential to critical industries like healthcare, transportation, and manufacturing, merging physical processes with computational intelligence. However, the security…
Homomorphic Encryption (HE) provides strong data privacy for cloud services but at the cost of prohibitive computational overhead. While GPUs have emerged as a practical platform for accelerating HE, there remains an order-of-magnitude…
Physics-informed neural networks (PINNs) is an emerging category of neural networks which can be trained to solve supervised learning tasks while taking into consideration given laws of physics described by general nonlinear partial…
Firmware refers to device read-only resident code which includes microcode and macro-instruction -level routines. For Internet-of-Things (IoT) devices without an operating system, firmware includes all the necessary instructions on how such…
The rapid adoption of the Internet of Medical Things (IoMT) is transforming healthcare by enabling seamless connectivity among medical devices, systems, and services. However, it also introduces serious cybersecurity and patient safety…
Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-only evaluation. In this paper, we present a systematic…
Kimi K2.5 is an open-weight LLM that rivals closed models across coding, multimodal, and agentic benchmarks, but was released without an accompanying safety evaluation. In this work, we conduct a preliminary safety assessment of Kimi K2.5…
Cyber-attacks continue to grow in scale and sophistication, yet existing network intrusion detection approaches lack the semantic depth required for path reasoning over attacker-victim interactions. We address this by first modelling…
LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. Unlike traditional packages, these skills are executed as operational directives with…
Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in privileged environments, making leakage risks poorly understood. We present the first large-scale empirical study of this problem,…
In a healthcare environment, the healthcare interoperability platforms based on HL7 FHIR allow concurrent, asynchronous access to a set of shared patient resources, which are independent systems, i.e., EHR systems, pharmacy systems, lab…
Agent Skills is an emerging open standard that defines a modular, filesystem-based packaging format enabling LLM-based agents to acquire domain-specific expertise on demand. Despite rapid adoption across multiple agentic platforms and the…
Providing reliable, affordable, and secure Internet connectivity in rural areas remains a major challenge. Pay-for-use Wi-Fi hotspots are emerging as a scalable solution to provide affordable Internet access in underserved and rural…
Smart contracts are increasingly targeted by adversaries employing obfuscation techniques such as bogus code injection and control flow manipulation to evade vulnerability detection. Existing multimodal methods often process semantic,…
When Agent A delegates to Agent B, which invokes Tool C on behalf of User X, no existing framework can answer: whose authorization chain led to this action, and where did it violate policy? This paper introduces SentinelAgent, a formal…
Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment for deployed frontier models, two separate lines of recent…
The increasing complexity and volume of software systems have heightened the importance of identifying and mitigating security vulnerabilities. The existing software vulnerability datasets frequently fall short in providing comprehensive,…