cs.CR · 2026-06-23 · No. 32

Cryptography and Security, 2026-06-23.

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

01 — The papers

4 entries
  1. 01

    Detecting Malicious Agent Skills in the Wild using Attention

    Bacem Etteib, Daniele Lunghi, Tégawendé F. Bissyandé

    cs.CR · cs.AI

    LLM agents increasingly load skills, file-based packages of natural-language instructions written by third parties and distributed through marketplaces, that execute with the user's privileges. A single malicious skill can exfiltrate data, hijack the agent, or persist as a supply-chain foothold, which turns the skill marketplace into a new attack surface for agentic systems. Prompt-injection defenses do not carry over to this setting. They...

    arxiv.org/abs/2606.23416 · PDF

  2. 02

    FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

    Yinpeng Wu, Yitong Chen, Lixiang Wang, Jinyu Gu, Zhichao Hua, Yubin Xia

    cs.CR · cs.LG · cs.OS

    Device-side Large Language Models (LLMs) have grown explosively, offering stronger privacy and higher availability than their cloud-side counterparts. During LLM inference, both the model weights and the user data are valuable, and attackers may compromise the OS kernel to steal them. ARM TrustZone is the de facto hardware-based isolation technology on mobile devices, used to protect sensitive applications from a compromised OS. However,...

    arxiv.org/abs/2606.23370 · PDF

  3. 03

    Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies

    Ruixiao Lin, Xinhao Deng, Qingming Li, Jianan Ma, Yunhao Feng, Yuqi Qing, Zhenyuan Li, Yechao Zhang, Shiwen Cui,...

    cs.CR · cs.AI

    Self-evolving LLM agent systems, which autonomously update their model parameters, memory, tools, and architectures, introduce a qualitatively new threat landscape in which adversarial influences become permanently encoded, self-amplify across generations, and propagate through populations without sustained attacker access. We present a systematic security and privacy analysis organized around the Module-Lifecycle Attack Surface (MLAS)...

    arxiv.org/abs/2606.23075 · PDF

  4. 04

    CITADEL: CSI-Based Jamming Detection and Open-Set Classification for IIoT Networks

    Aymen Bouferroum, Ildi Alla, Valeria Loscri, Abderrahim Benslimane, Vincent Lenders

    cs.CR · cs.LG · cs.NI

    Radio frequency jamming poses a critical threat to the availability of wireless Industrial Internet of Things (IIoT) networks. Existing detection and classification techniques are poorly suited to this setting: coarse signal-strength and cross-layer features lack information richness, while raw I/Q baseband approaches require hardware and throughput that is impractical at the scale of hundred-node IIoT deployments. This paper presents...

    arxiv.org/abs/2606.22939 · 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.