cyberintel.kalymoon.com · 4648 articles · updated every 4 hours · grows forever
arXiv:2606.15242v1 Announce Type: new Abstract: Skills are becoming the capability layer through which LLM agents turn plans into actions, but their use introduces security risks such as data leakage,…
arXiv:2606.15229v1 Announce Type: new Abstract: Network scanning is a critical preliminary step for most adversaries to gain essential information before launching cyber attacks. Moving Target Defense…
arXiv:2606.15221v1 Announce Type: new Abstract: Air fingerprinting infers application activity by sniffing metadata from cellular control channels. 5G encrypts these channels, breaking the attack chai…
arXiv:2606.15165v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models enable end-to-end robot control and have garnered widespread attention. However, the memorization of training data i…
arXiv:2606.15123v1 Announce Type: new Abstract: We study the task of CVE-conditioned exploit generation, where a model drafts proof-of-concept (PoC) exploits given software vulnerability context. We a…
arXiv:2606.15093v1 Announce Type: new Abstract: Previous FPSI works have demonstrated a linear scaling with the distance threshold $\delta$, while some recent works have achieved a poly-logarithmic de…
arXiv:2606.15057v1 Announce Type: new Abstract: Indirect prompt injection (IPI) is a major security threat to LLM-powered agents. Thus, a growing body of work have proposed a variety of defensive appr…
arXiv:2606.15047v1 Announce Type: new Abstract: Moving Target Defense (MTD) is a proactive security strategy designed to enhance cyber-resilience by dynamically altering system parameters, thereby pre…
arXiv:2606.15020v1 Announce Type: new Abstract: Document-to-LLM applications typically read uploaded PDFs by first translating them into text through a hidden extraction layer that users cannot observ…
arXiv:2606.15008v1 Announce Type: new Abstract: Agentic large language model (LLM) systems can now execute actions, not only produce text. When model outputs trigger privileged operations such as shel…
arXiv:2606.14987v1 Announce Type: new Abstract: Internet of Things (IoT) and Cyber-physical systems (CPS) increasingly rely on continual learning (CL) to adapt to evolving environments, device heterog…
arXiv:2606.14939v1 Announce Type: new Abstract: Auctions are now central to blockchain markets, settling NFT sales, token launches, DeFi liquidations, and arbitrage opportunities. Each on-chain bid is…
arXiv:2606.14831v1 Announce Type: new Abstract: This paper presents and characterizes a spectrum of previously unreported behaviours we term Constraint-Evasive Fabrication (CEF): when an LLM agent ope…
arXiv:2606.14816v1 Announce Type: new Abstract: This paper presents a structured analysis of security challenges in long-horizon agentic AI systems. The study reviews existing threats, evaluation appr…
This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. When I landed in Seoul after a grueling 12-hour flight from Sa…
Google has announced a $1.5 billion investment for 2026 and 2027 to expand its data center campus in Jackson County, Alabama. Operating since 2019 on a repurposed former…
arXiv:2606.14415v1 Announce Type: new Abstract: Safe reinforcement learning (Safe RL) aims to maximize expected return while satisfying safety constraints, typically modeled as Constrained Markov Deci…
arXiv:2606.14314v1 Announce Type: new Abstract: LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, whi…
arXiv:2606.14249v1 Announce Type: new Abstract: AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observe…
arXiv:2606.14240v1 Announce Type: new Abstract: Affordance reasoning, the inference of an object's action possibilities from its physical properties (e.g., shape and material), is fundamental to human…
arXiv:2606.14239v1 Announce Type: new Abstract: Agent skills are structured procedural packages that guide frozen LLM agents in specialized workflows. Skills rarely remain sufficient after deployment:…
arXiv:2606.14211v1 Announce Type: new Abstract: LLMs are increasingly deployed as agents that interact with external environments and observe feedback such as execution results, error messages, and to…
arXiv:2606.14200v1 Announce Type: new Abstract: Open platforms increasingly route tasks among heterogeneous LLM agents--differing in base model, scaffold, and tool stack--whose competence varies sharp…
arXiv:2606.14176v1 Announce Type: new Abstract: Geometry problem generation is useful for AI-assisted education and multimodal mathematical reasoning, but reliable synthesis remains difficult because …