密码学与安全

Knowledge distillation from proprietary LLM APIs poses a growing threat to model providers, yet defenses against this attack remain fragmented and unevaluated. We present DistillGuard, a framework for systematically evaluating output-level…

In today's technology-driven world, web services have opened up new opportunities for blind and visually impaired people to interact independently. Securing interactions with these services is crucial; however, currently deployed…

Collaborative threat intelligence via federated learning (FL) faces critical risks from quantum computing, which can compromise classical encryption methods. This study proposes a quantum-secure FL framework using post-quantum cryptography…

Trust management is a critical research pillar in Vehicular Ad Hoc Networks (VANETs), where the reliability of shared data depends entirely on driver integrity. In these networks, a driver's reputation is dynamically constructed based on…

This Systematization of Knowledge (SoK) provides a comprehensive historical analysis of Maximal Extractable Value (MEV) in blockchain systems, tracing its conceptual evolution through three distinct eras. We organize the fragmented…

Certified deletion ensures that encrypted data can be irreversibly deleted, preventing future recovery even if decryption keys are later exposed. Although existing works have achieved certified deletion across various cryptographic…

Membership inference attacks (MIAs) have become the standard tool for evaluating privacy leakage in machine learning (ML). Among them, the Likelihood-Ratio Attack (LiRA) is widely regarded as the state of the art when sufficient shadow…

The Model Context Protocol (MCP) is an open and standardized interface that enables large language models (LLMs) to interact with external tools and services, and is increasingly adopted by AI agents. However, the security of MCP-based…

Cloud-based infrastructures have become the dominant platform for deploying large models, particularly large language models (LLMs). Fine-tuning and inference are increasingly delegated to cloud providers for simplified deployment and…

Large Language Models (LLMs) are increasingly integrated into safety-critical workflows, yet existing security analyses remain fragmented and often isolate model behavior from the broader system context. This work introduces a goal-driven…

Backdoor mechanisms have traditionally been studied as security threats that compromise the integrity of machine learning models. However, the same mechanism -- the conditional activation of specific behaviors through input triggers -- can…

Website fingerprinting (WF) attacks on Tor can infer user destinations from encrypted traffic metadata. However, their real-world effectiveness remains debated due to laboratory settings that fail to capture network fluctuations, evaluate…

We study the problem of coded caching with nonuniform file popularity under the setting where the popularity distribution is initially unknown. By reframing the problem, we propose a method inspired by an algorithm from the…

In the present paper we study a non-modular variant of the Short Integer Solution problem over the integers. Given a random matrix $A \in \mathbb{Z}^{n\times m}$ with entries $a_{ij}$ such that $0\le a_{ij}< Q,$ for some $Q>0,$ the goal is…

As autonomous AI agents increasingly populate the Internet, a novel security challenge arises: "Is this entity an AI agent?" It is a new entity-type verification problem with no established solution. We formalize the problem through a…

As Joint Audio-Visual Generation Models see widespread commercial deployment, embedding watermarks has become essential for protecting vendor copyright and ensuring content provenance. However, existing techniques suffer from an…

Searchable Symmetric Encryption (SSE) allows users to search over encrypted data stored on untrusted servers, like cloud providers. While SSE hides the content of queries and documents, it still leaks patterns, such as how often a query is…

Recent text-to-video (T2V) models can synthesize complex videos from lightweight natural language prompts, raising urgent concerns about safety alignment in the event of misuse in the real world. Prior jailbreak attacks typically rewrite…

Consent-Based Access Control (CBAC) is a foundational mechanism for enforcing patient autonomy in modern healthcare information systems. Many CBAC frameworks are built on the eXtensible Access Control Markup Language (XACML) and inherit its…

Effective healthcare delivery depends on accurate longitudinal health records and addressing patients' concerns regarding the privacy of their information. While patient authentication is essential, reusing patient identifiers exposes…