密码学与安全

Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly…

Large Language Models (LLMs) are increasingly deployed across diverse domains, yet their vulnerability to jailbreak attacks, where adversarial inputs bypass safety mechanisms to elicit harmful outputs, poses significant security risks.…

Cyber Threat Intelligence (CTI) reports contain Indicators of Compromise (IOCs) that are critical for security operations. To operationalize these IOCs across heterogeneous logs, analysts often convert them into regular expressions…

The widespread use of Large Language Models (LLMs) in text generation has raised increasing concerns about intellectual property disputes. Watermarking techniques, which embed meta information into AI-generated content (AIGC), have the…

Protecting sensitive visual content from unauthorized redistribution is a growing challenge for privacy focused mobile applications, including dating platforms. Screenshot prevention mechanisms, rely on server side monitoring or are limited…

We present COBALT-TLA, a neuro-symbolic verification loop that pairs an LLM with TLC, the TLA+ model checker, in an automated REPL. The LLM generates bounded TLA+ specifications; TLC acts as a semantic oracle; structured error traces are…

The applications of Generative Artificial Intelligence (GenAI) and their intersections with data-driven fields, such as healthcare, finance, transportation, and information security, have led to significant improvements in service…

Coding agents and LLM-powered applications routinely send potentially sensitive content to cloud LLM APIs where it may be logged, retained, used for training, or subpoenaed. Existing privacy tooling focuses on network-level encryption and…

A recent and exciting thread of work focuses on developing methods for watermarking the output of large language models (LLMs). We focus on provably undetectable watermarking-that is, schemes that do not alter the output distribution of the…

We present SIR-Bench, a benchmark of 794 test cases for evaluating autonomous security incident response agents that distinguishes genuine forensic investigation from alert parroting. Derived from 129 anonymized incident patterns with…

This study evaluates the feasibility of integrating lightweight block cipher payload encryption into a real-time embedded controller area network (CAN) node using a QT PY ESP32-S2 microcontroller. This work seeks to determine whether the…

Apple AirTags use Apple's Find My network: when nearby iDevices detect a lost tag, they anonymously forward an encrypted location report to Apple, which the tag's owner can then fetch to locate the item. That encryption protects privacy --…

Quantum computing simulators form the classical software foundation on which virtually all quantum algorithm research depends. We present Broken Quantum, the first comprehensive formal security audit of the open-source quantum computing…

Matchmaking has become a prevalent part in contemporary applications, being used in dating apps, social media, online games, contact tracing and in various other use-cases. However, most implementations of matchmaking require the collection…

European digital identity initiatives are grounded in regulatory frameworks designed to ensure interoperability and robust, harmonized security standards. The evolution of these frameworks culminates in eIDAS 2.0, whose origins trace back…

Traditional approaches for smart contract analysis often rely on intermediate representations such as abstract syntax trees, control-flow graphs, or static single assignment form. However, these methods face limitations in capturing both…

Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains of thought (CoT). However, these models introduce novel…

Psychological stress is a widespread issue that significantly impacts student well-being and academic performance. Effective remote stress recognition is crucial, yet existing methods often rely on wearable devices or GPS-based clustering…

Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic…

Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security…