密码学与安全

Client-side privacy rewriting is crucial for deploying LLMs in privacy-sensitive domains. However, existing approaches struggle to balance privacy and utility. Full-text methods often distort context, while span-level approaches rely on…

Large Language Model (LLM) agents are increasingly integrated into critical systems, leveraging external tools to interact with the real world. However, this capability exposes them to Indirect Prompt Injection (IPI), where attackers embed…

The rapid development and integration of intelligent technologies in the Internet of Vehicles (IoV) have revolutionized transportation systems by enhancing connectivity, automation, and safety. However, the complexity and connectivity of…

Large language models (LLMs) have recently emerged as promising tools for augmenting Security Operations Center (SOC) workflows, with vendors increasingly marketing autonomous AI solutions for SOCs. However, there remains a limited…

Transformer inference in machine-learning-as-a-service (MLaaS) raises privacy concerns for sensitive user inputs. Prior secure solutions that combine fully homomorphic encryption (FHE) and secure multiparty computation (MPC) are…

We design and develop a secret-sharing-scheme-based cyberattack detection model(S3CDM)that can detect unauthorized or illegal activities (especially insider attacks) and protect sensitive information within complex network infrastructures…

We study whether in-domain pretraining of Bidirectional Encoder Representations from Transformer (BERT) model improves subdomain-level detection of exfiltration at low false positive rates. While previous work mostly examines fine-tuned…

Large Reasoning Models (LRMs) have achieved remarkable performance across diverse domains, yet their decision-making under conflicting objectives remains insufficiently understood. This work investigates how LRMs respond to harmful queries…

Reinforcement Learning with Verifiable Rewards (RLVR) is an emerging paradigm that significantly boosts a Large Language Model's (LLM's) reasoning abilities on complex logical tasks, such as mathematics and programming. However, we…

Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or…

Large language models (LLMs) have emerged as a powerful tool for synthetic data generation. A particularly important use case is producing synthetic replicas of private text, which requires carefully balancing privacy and utility. We…

With the rapid advancement of decentralized applications, smart contract security faces severe challenges, particularly regarding atomicity violations in complex logic such as Oracle and NFT contracts. Rigid rule sets often limit…

While Chain-of-Thought (CoT) prompting has become a standard paradigm for eliciting complex reasoning capabilities in Large Language Models, it inadvertently exposes a new attack surface for backdoor attacks. Existing CoT backdoor attacks…

We prove that no continuous, utility-preserving wrapper defense-a function $D: X\to X$ that preprocesses inputs before the model sees them-can make all outputs strictly safe for a language model with connected prompt space, and we…

Digital devices like tablets, media players, and kiosks are increasingly deployed in U.S. prisons. These technologies can enable incarcerated people to access education, communicate with loved ones, and develop vital reentry skills.…

With frequently evolving Advanced Persistent Threats (APTs) in cyberspace, traditional security solutions approaches have become inadequate for threat hunting for organizations. Moreover, SOC (Security Operation Centers) analysts are often…

Capture The Flag (CTF) competitions have established themselves as a highly effective pedagogical tool in cybersecurity education, offering students hands-on experience in realistic attack and defense scenarios. However, organizing and…

In Shamir's secret sharing scheme, all participants possess equal privileges. However, in many practical scenarios, it is often necessary to assign different levels of authority to different participants. To address this requirement,…

This paper emphasizes the critical role of interoperability in enabling efficient and secure communication for the fragmented distributed ledger ecosystem, particularly within on-chain finance. The purpose of this study is to streamline and…

Given limited and costly computational infrastructure, resource efficiency is a key requirement for large language models (LLMs). Efficient LLMs increase service capacity for providers and reduce latency and API costs for users. Recent…