cyberintel.kalymoon.com · 49667 articles · updated every 4 hours · grows forever
arXiv:2603.23676v1 Announce Type: new Abstract: We study long-horizon planning in 3D environments from under-specified natural-language goals using only visual observations, focusing on multi-step 3D …
arXiv:2603.23660v1 Announce Type: new Abstract: We introduce GTO Wizard Benchmark, a public API and standardized evaluation framework for benchmarking algorithms in Heads-Up No-Limit Texas Hold'em (HU…
arXiv:2603.23638v1 Announce Type: new Abstract: Large language models (LLMs) have enabled agentic systems that can reason, plan, and act across complex tasks, but it remains unclear whether they can a…
arXiv:2603.23625v1 Announce Type: new Abstract: Artificial intelligence (AI) is increasingly being explored in health and social care to reduce administrative workload and allow staff to spend more ti…
arXiv:2603.23610v1 Announce Type: new Abstract: Although large language models (LLMs) have advanced rapidly, robust automation of complex software workflows remains an open problem. In long-horizon se…
arXiv:2603.23539v1 Announce Type: new Abstract: We show that PLDR-LLMs pretrained at self-organized criticality exhibit reasoning at inference time. The characteristics of PLDR-LLM deductive outputs a…
arXiv:2508.02116v2 Announce Type: replace Abstract: As a versatile AI application, voice assistants (VAs) have become increasingly popular, but are vulnerable to security threats. Attackers have propo…
arXiv:2507.22171v3 Announce Type: replace Abstract: Jailbreak attacks aim to exploit large language models (LLMs) by inducing them to generate harmful content, thereby revealing their vulnerabilities.…
arXiv:2603.24511v1 Announce Type: cross Abstract: LLM agents like Claude Code can not only write code but also be used for autonomous AI research and engineering \citep{rank2026posttrainbench, novikov…
arXiv:2603.24282v1 Announce Type: cross Abstract: Modern software systems heavily rely on third-party dependencies, making software supply chain security a critical concern. We introduce the concept o…
arXiv:2603.24232v1 Announce Type: cross Abstract: Machine learning models trained on small data sets for security applications are especially vulnerable to adversarial attacks. Person identification f…
arXiv:2603.24079v1 Announce Type: cross Abstract: Recently, multimodal large language models (MLLMs) have emerged as a unified paradigm for language and image generation. Compared with diffusion model…
arXiv:2603.23509v1 Announce Type: cross Abstract: This work identifies a critical failure mode in frontier large language models (LLMs), which we term Internal Safety Collapse (ISC): under certain tas…
arXiv:2603.24564v1 Announce Type: new Abstract: Every API token you spend is your accumulated wealth; once you can prove its value and the effort behind it, you can resell it. As autonomous agents rep…
arXiv:2603.24543v1 Announce Type: new Abstract: Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unrelia…
arXiv:2603.24426v1 Announce Type: new Abstract: The advent of quantum computing will pose great challenges to the current communication systems, requiring essential changes in the establishment of sec…
arXiv:2603.24414v1 Announce Type: new Abstract: OpenClaw has rapidly established itself as a leading open-source autonomous agent runtime, offering powerful capabilities including tool integration, lo…
arXiv:2603.24302v1 Announce Type: new Abstract: Telegram, initially a messaging app, has evolved into a platform where users can interact with various services through programmable applications, bots.…
arXiv:2603.24203v1 Announce Type: new Abstract: Recent advances in the Model Context Protocol (MCP) have enabled large language models (LLMs) to invoke external tools with unprecedented ease. This cre…
arXiv:2603.24172v1 Announce Type: new Abstract: Microarchitectural vulnerabilities increasingly undermine the assumption that hardware can be treated as a reliable root of trust. Prevention mechanisms…
arXiv:2603.24167v1 Announce Type: new Abstract: WebAssembly's (Wasm) monolithic linear memory model facilitates memory corruption attacks that can escalate to cross-site scripting in browsers or go un…
arXiv:2603.24111v1 Announce Type: new Abstract: The Industrial Internet of Things (IIoT) introduces significant security challenges as resource-constrained devices become increasingly integrated into …
arXiv:2603.24003v1 Announce Type: new Abstract: Differential privacy (DP) is crucial for safeguarding sensitive client information in federated learning (FL), yet traditional DP-FL methods rely predom…
arXiv:2603.23996v1 Announce Type: new Abstract: The proliferation of local Large Language Model (LLM) runners, such as Ollama, LM Studio and llama.cpp, presents a new challenge for digital forensics i…