cyberintel.kalymoon.com · 4867 articles · updated every 4 hours · grows forever
arXiv:2604.18873v1 Announce Type: new Abstract: Large language models (LLMs) are highly capable at language generation, but they remain unreliable when reasoning requires explicit symbolic structure, …
arXiv:2604.18847v1 Announce Type: new Abstract: As LM agents gain the ability to execute actions on real computer systems, we need ways to not only prevent harmful actions at scale but also effectivel…
arXiv:2604.18838v1 Announce Type: new Abstract: This research investigates the performance and efficacy of machine learning models in stock prediction, comparing Artificial Neural Networks (ANNs), Qua…
arXiv:2604.18805v1 Announce Type: new Abstract: Large language model (LLM)-based systems are increasingly deployed to conduct scientific research autonomously, yet whether their reasoning adheres to t…
arXiv:2604.18789v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical vulnerability: an im…
arXiv:2604.18724v1 Announce Type: new Abstract: Users typically interact with and evaluate language models via single outputs, but each output is just one sample from a broad distribution of possible …
arXiv:2604.18645v1 Announce Type: new Abstract: This paper addresses the Variable Gapped Longest Common Subsequence (VGLCS) problem, a generalization of the classical LCS problem involving flexible ga…
arXiv:2604.19711v1 Announce Type: new Abstract: We analyse the 2025 Signalgate leak of sensitive US military information by the Trump administration, addressing why confidentiality was violated (messa…
arXiv:2604.19657v1 Announce Type: new Abstract: AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data (e.g., person…
arXiv:2604.19628v1 Announce Type: new Abstract: The binary executable format is the standard method for distributing and executing software. Yet, it is also as opaque a representation of software as c…
arXiv:2604.19533v1 Announce Type: new Abstract: We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model (LLM) agents perform the core SOC analyst task of thre…
arXiv:2604.19526v1 Announce Type: new Abstract: Cross-site scripting (XSS) remains a persistent web security vulnerability, especially because obfuscation can change the surface form of a malicious pa…
arXiv:2604.19496v1 Announce Type: new Abstract: BusyBox is one of the most widely reused userland components in Linux-based Internet-of-Things (IoT) firmware, yet its security assessment remains diffi…
arXiv:2604.19471v1 Announce Type: new Abstract: This paper presents Map Reduce Graph (MRG), a novel unsupervised method for modeling and securing HTTP REST APIs. MRG learns API structure from real-wor…
arXiv:2604.19461v1 Announce Type: new Abstract: Safety alignment in large language models relies on behavioral training that can be overridden when sufficiently strong in-context patterns compete with…
arXiv:2604.19438v1 Announce Type: new Abstract: Pre-trained machine learning models (PTMs) are commonly provided via Model Hubs (e.g., Hugging Face) in standard formats like Pickles to facilitate acce…
arXiv:2604.19422v1 Announce Type: new Abstract: With the growing use of eye tracking on VR and mobile platforms, gaze data is increasing. While scanpath comparison is important to gaze behavior analys…
arXiv:2604.19219v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative model training among multiple parties without centralizing raw data. There are two main paradigms in FL: H…
arXiv:2604.19118v1 Announce Type: new Abstract: Modern distributed systems generate massive volumes of log data that are critical for detecting anomalies and cyber threats. However, in real world sett…
arXiv:2604.19090v1 Announce Type: new Abstract: The rapid adoption of diffusion-based generative models has intensified concerns over the attribution and integrity of AI-generated content (AIGC). Exis…
arXiv:2604.19083v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatene…
arXiv:2604.19053v1 Announce Type: new Abstract: We propose CHRONOS, a hardware-assisted framework that decouples the cryptographic setup required for private gradient aggregation from the active train…
arXiv:2604.19049v1 Announce Type: new Abstract: LLM-assisted defect discovery has a precision crisis: plausible-but-wrong reports overwhelm maintainers and degrade credibility for real findings. We pr…
arXiv:2604.19031v1 Announce Type: new Abstract: Software vulnerabilities are a primary threat to modern infrastructure. While static analysis and Graph Neural Networks have long served as the foundati…