cs.CR · 2026-10-21 · No. 150

Cryptography and Security, 2026-10-21.

6 new papers in cs.CR. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

6 entries
  1. 01

    A Digital Twin to Improve Cyber-Social Impact

    Vita Santa Barletta, Danilo Caivano, Gabriel Cellammare, Andrea Dimauro, Pasquale Mesagna, Massimiliano Morga

    cs.CR · cs.AI

    The increasing complexity of Industrial Control Systems (ICS) and their integration with IT infrastructures has significantly expanded the cyber threat landscape. Traditional cybersecurity models, primarily based on the Confidentiality, Integrity, and Availability (CIA triad), fail to capture the broader societal and operational impacts of cyberattacks. This paper proposes a novel framework that integrates Digital Twin technology with a...

    arxiv.org/abs/2610.28430 · PDF

  2. 02

    After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents

    Zhiyue Xu, Xukai Wang, Zhiyuan Huang, Mingjie Zhan, Jian Zhao, Xu-Yao Zhang

    cs.CR · cs.AI

    Modern LLM agents persist state across sessions via two channels: long-lived memory files silently prepended to the system prompt, and scheduled tasks waking the agent without user input. A one-time indirect prompt injection committed to either channel can re-fire across sessions long after the attacker leaves, threats we term carryover attacks. Existing prompt-injection benchmarks evaluate attacks only in the session where malicious content...

    arxiv.org/abs/2610.28425 · PDF

  3. 03

    MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems

    Mohammad Kachuee, Phu Mon Htut, Sheng Li, Nikolaos Pappas, Miguel Ballesteros Martinez, Yassine Benajiba, Sujith...

    cs.CR · cs.AI · cs.CL

    Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, substantially expanding their utility while exposing applications to unsafe actions, information leakage, and adversarial manipulation. Multi-agent systems further expand these capabilities through specialization and collaboration, but distributed authority, heterogeneous roles, and opaque or potentially compromised...

    arxiv.org/abs/2610.28397 · PDF

  4. 04

    Context-Aware Prompt Injection Detection via Small Language Models in RAG Pipelines: nokast-secureRAG

    Abhishek Rai

    cs.CR · cs.AI

    Local Retrieval-Augmented Generation (RAG) systems are vulnerable to indirect prompt injection and retrieval poisoning, where malicious instructions in retrieved content are mistaken for trusted input. We present nokast-secureRAG, a roughly 0.5B-parameter small language model that acts as a semantic firewall between retrieval and generation. It jointly evaluates the user query and retrieved context, classifying the pair as safe, suspicious,...

    arxiv.org/abs/2610.28364 · PDF

  5. 05

    Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory

    Masahiro Kaneko, Hiromi Arai, Timothy Baldwin

    cs.CR · cs.CL · cs.LG

    Large language model (LLM) agents increasingly use persistent memory to personalize responses, and personal attributes in this memory pose a privacy risk if exposed. We ask how consulting memory during dialogue changes what users go on to say, and thus what the memory comes to reveal. In multi-session simulations, a simulated user with 24 personal attributes talks with a support agent that does or does not consult memory, and in both settings...

    arxiv.org/abs/2610.28315 · PDF

  6. 06

    ClawMMU: Protection-Coherent Virtual Memory for Stateful LLM Agents

    Jinhao Hu, Bardia Mohammadi, Mofasshara Binte Rafique, Lars Henning Klein, Akhil Arora, Ashvin Goel, Laurent Bindschaedler

    cs.CR · cs.AI · cs.OS

    AI agents keep long-term memory, much of which comes from web pages and tool results. Agent harnesses, the software that runs the model, do not record who may act on this memory, so an instruction hidden in a fetched page can be treated as the user's own instruction. We propose ClawMMU, a protection layer that labels every piece of memory with its owner, scope, origins, and authority. ClawMMU checks these labels whenever content enters the...

    arxiv.org/abs/2610.28093 · PDF

This edition is part of The Daily Abstract — cs.CR archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.