cyberintel.kalymoon.com · 2756 articles · updated every 4 hours · grows forever
arXiv:2604.00362v1 Announce Type: new Abstract: No one has independently reproduced OpenAI's published scores for gpt-oss-20b with tools, because the original paper discloses neither the tools nor the…
arXiv:2604.00356v1 Announce Type: new Abstract: Agentic applications based on large language models increasingly rely on multi-step interaction loops involving planning, action execution, and environm…
arXiv:2604.00319v1 Announce Type: new Abstract: We develop algorithms for collaborative control of AI agents and critics in a multi-actor, multi-critic federated multi-agent system. Each AI agent and …
arXiv:2604.00284v1 Announce Type: new Abstract: We formally introduce a improvisational wordplay game called Connections to explore reasoning capabilities of AI agents. Playing Connections combines sk…
arXiv:2604.00281v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in computer science education through AI-assisted programming tools, yet such workflows often exh…
arXiv:2604.00249v1 Announce Type: new Abstract: Single-agent large language model (LLM) systems struggle to simultaneously support diverse conversational functions and maintain safety in behavioral he…
arXiv:2604.00137v1 Announce Type: new Abstract: Tool-integrated LLMs can retrieve, compute, and take real-world actions via external tools, but reliability remains a key bottleneck. We argue that fail…
arXiv:2604.00085v1 Announce Type: new Abstract: Large language models applied to clinical prediction exhibit case-level heterogeneity: simple cases yield consistent outputs, while complex cases produc…
arXiv:2604.00005v1 Announce Type: new Abstract: Emotion plays an important role in human cognition and performance. Motivated by this, we investigate whether analogous emotional signals can shape the …
arXiv:2604.00942v1 Announce Type: cross Abstract: We introduce a differentially private manifold denoising framework that allows users to exploit sensitive reference datasets to correct noisy, non-pri…
arXiv:2604.00887v1 Announce Type: cross Abstract: Deep neural networks have demonstrated excellent performance in SAR target detection tasks but remain susceptible to adversarial attacks. Existing SAR…
arXiv:2604.00788v1 Announce Type: cross Abstract: This technical report presents methods developed by the UK AI Security Institute for assessing whether advanced AI systems reliably follow intended go…
arXiv:2604.00761v1 Announce Type: cross Abstract: Existing research on privacy-preserving Human Activity Recognition (HAR) typically evaluates methods against a binary paradigm: clear video versus a s…
arXiv:2604.00741v1 Announce Type: cross Abstract: Random Number Generators (RNGs) are crucial for applications ranging from cryptography to simulations. Depending on the source of randomness, RNGs are…
arXiv:2604.00702v1 Announce Type: cross Abstract: Due to their widespread use in industry, several techniques have been proposed in the literature to fuzz REST APIs. Existing fuzzers for REST APIs hav…
arXiv:2604.00657v1 Announce Type: cross Abstract: Smart contracts are self-executing programs that manage financial transactions on blockchain networks. Developers commonly rely on third-party code li…
arXiv:2604.00430v1 Announce Type: cross Abstract: Large language model (LLM)-based agents have recently gained considerable attention due to the powerful reasoning capabilities of LLMs. Existing resea…
arXiv:2604.01194v1 Announce Type: new Abstract: Large language models (LLMs) and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injectio…
arXiv:2604.01131v1 Announce Type: new Abstract: Code obfuscation is widely adopted in modern software development to protect intellectual property and hinder reverse engineering, but it also provides …
arXiv:2604.01127v1 Announce Type: new Abstract: Software-Defined Networking (SDN) is increasingly adopted to secure Internet-of-Things (IoT) networks due to its centralized control and programmable fo…
arXiv:2604.01092v1 Announce Type: new Abstract: WiFi is inherently vulnerable to eavesdropping because RF signals may penetrate many physical boundaries, such as walls and floors. LiFi, by contrast, i…
arXiv:2604.01079v1 Announce Type: new Abstract: There is a growing need for cybersecurity professionals with practical knowledge and experience to meet societal needs and comply with new standards and…
arXiv:2604.01052v1 Announce Type: new Abstract: "Vibe coding," in which developers delegate code generation to AI assistants and accept the output with little manual review, has gained rapid adoption …
arXiv:2604.01039v1 Announce Type: new Abstract: System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operation…