cyberintel.kalymoon.com · 2889 articles · updated every 4 hours · grows forever
arXiv:2603.26838v1 Announce Type: new Abstract: This paper surveys uncertainty-aware explainable artificial intelligence (UAXAI), examining how uncertainty is incorporated into explanatory pipelines a…
arXiv:2603.26782v1 Announce Type: new Abstract: Text-to-level generation aims to translate natural language descriptions into structured game levels, enabling intuitive control over procedural content…
arXiv:2603.26765v1 Announce Type: new Abstract: The efficiency of game engines and policy optimization algorithms is crucial for training reinforcement learning (RL) agents in complex sequential decis…
arXiv:2603.28654v1 Announce Type: new Abstract: Network security threats in embedded systems pose significant challenges to critical infrastructure protection. This paper presents a comprehensive fram…
arXiv:2603.28626v1 Announce Type: new Abstract: The transition to a cloud-native 5G Service-Based Architecture (SBA) improves scalability but exposes control-plane signaling to emerging quantum threat…
arXiv:2603.28551v1 Announce Type: new Abstract: Personalized computer-use agents are rapidly moving from expert communities into mainstream use. Unlike conventional chatbots, these systems can install…
arXiv:2603.28434v1 Announce Type: new Abstract: The synergy between Federated Learning and blockchain has been considered promising; however, the computationally intensive nature of contribution measu…
arXiv:2603.28313v1 Announce Type: new Abstract: Recently, a two-way RFID authentication protocol based on the AM-SUEO-DBLTKM variable matrix encryption algorithm was proposed for low-cost mobile RFID …
arXiv:2603.28309v1 Announce Type: new Abstract: Vulnerability detection in C programs is a critical challenge in software security. Although large language models (LLMs) achieve strong detection perfo…
arXiv:2603.28166v1 Announce Type: new Abstract: Equipping LLM agents with real-world tools can substantially improve productivity. However, granting agents autonomy over tool use also transfers the as…
arXiv:2603.28143v1 Announce Type: new Abstract: As machine learning as a service (MLaaS) gains increasing popularity, it raises two critical challenges: privacy and verifiability. For privacy, clients…
arXiv:2603.28043v1 Announce Type: new Abstract: Illicit online promotion is a persistent threat that evolves to evade detection. Existing moderation systems remain tethered to platform-specific superv…
arXiv:2603.28013v1 Announce Type: new Abstract: We present a stage-decomposed analysis of prompt injection attacks against five frontier LLM agents. Prior work measures task-level attack success rate …
arXiv:2603.27986v1 Announce Type: new Abstract: Federated learning (FL) enables distributed clients to collaboratively train a global model using local private data. Nevertheless, recent studies show …
arXiv:2603.27918v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabil…
arXiv:2603.27883v1 Announce Type: new Abstract: Reliable use of real-world data requires confidence that recorded evidence reflects what actually occurred at the moment of capture. In adversarial or i…
arXiv:2603.27739v1 Announce Type: new Abstract: Centralized stablecoins such as USDT and USDC enforce financial sanctions through contract-layer blacklist functions, yet on public blockchains a freeze…
arXiv:2603.27517v1 Announce Type: new Abstract: AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces--shell, filesystem, containers, and messaging--introduce …
arXiv:2603.27439v1 Announce Type: new Abstract: The dependability of AI models relies largely on the reliability of the underlying computation hardware. Hardware aging attacks can compromise the compu…
arXiv:2603.27326v1 Announce Type: new Abstract: Phishing attacks remain among the most prevalent cybersecurity threats, causing significant financial losses for individuals and organizations worldwide…
arXiv:2603.27204v1 Announce Type: new Abstract: Skills are increasingly used to extend LLM agents by packaging prompts, code, and configurations into reusable modules. As public registries and marketp…
arXiv:2603.27190v1 Announce Type: new Abstract: This paper extends the Kikuchi method to give algorithms for decisional $k$-sparse Learning With Errors (LWE) and $k$-sparse Learning Parity with Noise …
arXiv:2603.27148v1 Announce Type: new Abstract: When an LLM agent reads a confidential file, then writes a summary, then emails it externally, no single step is unsafe, but the sequence is a data leak…
arXiv:2603.27127v1 Announce Type: new Abstract: Web applications remain the dominant attack surface in cybersecurity, where vulnerabilities such as SQL injection, XSS, and business logic flaws continu…