arXiv:2610.08895v1 Announce Type: new Abstract: Finding severity is the main driver of how security teams prioritize remediation…
1 min Open reportarXiv:2610.08928v1 Announce Type: new Abstract: LLM-based agents are entering decision-support roles in defence staff work, where…
1 min Open reportarXiv:2610.08951v1 Announce Type: new Abstract: LLM agents retrieve untrusted content and act through tools, creating indirect…
1 min Open reportarXiv:2610.09012v1 Announce Type: new Abstract: Future generative patient digital twins may combine longitudinal health records…
1 min Open reportarXiv:2610.09027v1 Announce Type: new Abstract: Modern language model systems operate autonomously over increasingly long…
1 min Open reportarXiv:2610.09029v1 Announce Type: new Abstract: Organisations deciding which assets to migrate to post-quantum cryptography…
1 min Open reportarXiv:2610.09138v1 Announce Type: new Abstract: Autonomous and agentic clients can distribute reconnaissance across many…
1 min Open reportarXiv:2610.09240v1 Announce Type: new Abstract: Modern web agents built on large vision-language models process webpages, select…
1 min Open reportarXiv:2610.09264v1 Announce Type: new Abstract: Modern agentic coding frameworks increasingly rely on community-shared rule files…
1 min Open reportarXiv:2610.09337v1 Announce Type: new Abstract: Policy-based reinforcement learning (RL) approaches have produced promising…
1 min Open reportarXiv:2610.09469v1 Announce Type: new Abstract: Computer-use agents (CUAs) perform tasks across applications (such as desktops…
1 min Open reportarXiv:2610.09552v1 Announce Type: new Abstract: Watermarking enables language model providers to identify text generated by their…
1 min Open reportarXiv:2610.09553v1 Announce Type: new Abstract: Large language models can triage malware through direct verdicts or behavioral…
1 min Open reportarXiv:2610.09581v1 Announce Type: new Abstract: Forensic reconstruction of LLM-agent actions requires not only recovering the…
1 min Open reportarXiv:2610.09697v1 Announce Type: new Abstract: Threat analysis and risk assessment (TARA) according to ISO/SAE 21434 treats…
1 min Open reportarXiv:2610.09703v1 Announce Type: new Abstract: Token-Pruning accelerates Vision-Language Models by removing redundant visual…
1 min Open reportarXiv:2610.09708v1 Announce Type: new Abstract: Vision-Language-Action models (VLAs) are increasingly deployed in safety-critical…
1 min Open reportarXiv:2610.09730v1 Announce Type: new Abstract: Protocol verifiers check whether a protocol meets a security goal under stated…
1 min Open reportarXiv:2610.09767v1 Announce Type: new Abstract: The Polynomial Modular Number Systems (PMNS) aim to represent elements of fields…
1 min Open reportarXiv:2610.09793v1 Announce Type: new Abstract: Guardrails for tool-using LLM agents are usually application-specific rules…
1 min Open report