cs.CR · 2026-10-19 · No. 148

Cryptography and Security, 2026-10-19.

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

01 — The papers

5 entries
  1. 01

    HardEval: An Execution-Verified Benchmark for AI-Driven Security Hardening and Compliance Remediation

    Manohar Vellala, Soumya Banerjee, Sandip Roy, Ross Gore, Sachin Shetty

    cs.CR · cs.LG

    Implementing Security Technical Implementation Guide (STIG) controls remains a demanding operating-system administration task. Each natural-language security requirement must be translated into a precise and persistent configuration change. These changes span Secure Shell (SSH) configuration, authentication policy, audit rules, and kernel parameters. Existing benchmarks do not measure whether a model can perform this task on a live system....

    arxiv.org/abs/2610.23685 · PDF

  2. 02

    TUPLE-Bench: Evaluating and Mitigating Privacy-Utility Trade-offs in Typed Decision Models

    Yiqu Yang, Qiaoyuan Zheng, Yang Tian, Yu Fan, Elliott Ash

    cs.CR · cs.AI

    Typed decision models often return more than a selected category. They also expose probabilities for each candidate and, sometimes, a separate confidence score. These fields support downstream decisions but may reveal information beyond a recipient's authorization. We introduce TUPLE-Bench (Typed decision models' Utility and Privacy Leakage Evaluation Benchmark), a benchmark of paired synthetic cases in which recipients may learn a coarse...

    arxiv.org/abs/2610.23668 · PDF

  3. 03

    From Billion-Scale to Million-Scale Language Models: Operational Capabilities for Embedded Post-Exploitation

    Gabriel Hortea, Simon Pietro Romano, Juan Tapiador, Mario Varlese

    cs.CR · cs.AI

    Small Language Models (SLMs) are increasingly attractive for resource-constrained environments due to their low computational footprint. These characteristics also make them candidates for future autonomous malware, where connectivity, latency, privacy, or operational constraints may preclude cloud-based inference. Yet the ability of ultra-compact models to support malware during post-exploitation remains poorly understood. We systematically...

    arxiv.org/abs/2610.23534 · PDF

  4. 04

    MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection

    Songping Wang, Peiyang Li, Yi Huang, Fengting Li, Xuhao Ran, Yueming Lyu, Chao Feng, Caifeng Shan

    cs.CR · cs.AI

    Multimodal large language model (MLLM)-based mobile agents are rapidly evolving from conversational assistants into autonomous systems that perceive, reason over, and act on smartphone environments. This capability also exposes a new security risk: adversaries can embed malicious objectives in cross-application mobile content and steer agent behavior through indirect multimodal injection. Although prompt injection has been studied in desktop...

    arxiv.org/abs/2610.23307 · PDF

  5. 05

    On the (In)stability of Adaptive Fee Mechanisms in Multi-Chain Systems

    Yifan Zhou, Jiang Xiao, Xuechao Wang, Ru Cheng, Shijie Zhang

    cs.CR · cs.DC

    EIP-1559 has become the dominant transaction fee mechanism in permissionless blockchains, regulating scarce block space through an adaptive base fee. The design balances a trade-off between responsiveness to demand fluctuations and stability of long-term resource usage. On a single chain, this trade-off is well understood and empirically stable. In multi-chain systems, however, cross-chain flows introduce delayed economic interactions across...

    arxiv.org/abs/2610.23305 · 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.