cs.CR · 2026-08-30 · No. 100

Cryptography and Security, 2026-08-30.

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

    RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution

    Junjie Zhang, Hui Liu, Kecheng Chen, Xianbo Mo, Changsheng Chen, Haoliang Li

    cs.CR · cs.AI

    LLM-based agents are increasingly deployed in product-level execution harnesses, where jailbreaks can trigger harmful tool use and persistent state changes, creating greater risks than unsafe text generation alone. Existing automatic red-teaming methods often rely on fixed attacks, while recent agentic attackers coordinate multiple jailbreak tools and show stronger potential through trajectory-based retrieval. However, such retrieval can...

    arxiv.org/abs/2608.27439 · PDF

  2. 02

    Beyond F1: Evaluating Coverage and Failure Recovery in AI Model Security Scanners

    Qianlong Lan, Vinothini Pandurangan, Anuj Kaul, Indranil Sanyal

    cs.CR · cs.AI

    Static scanners are increasingly used to identify executable or otherwise unsafe content in machine- learning artifacts, yet conventional evaluation metrics characterize only cases where a scanner yields a usable security judgment. We evaluate ModelScan, ModelAudit, and Fickling using a controlled, artifact-backed benchmark on a synthetic corpus of 170 Pickle and PyTorch focused artifacts across 145 specimen families, 135 of which have binary...

    arxiv.org/abs/2608.27424 · PDF

  3. 03

    Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents

    Chenhao Wu, Haoxuan Jia, Yang Liu, Yingguang Yang, Yuhan Lin, Chongyang Zhang, Hao Zheng, Yulin Huang, Jianshen...

    cs.CR · cs.AI

    Large language model agents are increasingly deployed as autonomous loops. Starting from one human goal, such a system repeatedly discovers work, plans, executes tool calls, verifies outcomes and persists state across many unattended iterations. The agent safeguards in wide use, however, are defined over a single trajectory, and their safety state is re-initialized when the next trajectory begins. We show that this is a failure of composition...

    arxiv.org/abs/2608.27141 · PDF

  4. 04

    SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoring

    Baran Can Gül, Hanuma Siddhartha Tunuguntla, Anjana Arvind Naik, Abhishek Vijay Potekar, Nasser Jazdi, Michael Weyrich

    cs.CR · cs.LG

    Federated Learning (FL) enables privacy-aware distributed training, yet gradient updates remain exploitable: Man-in-the-Middle (MitM) interception exposes updates in transit, while model poisoning corrupts global convergence. We first introduce GASHE (Gradient-Aware Selective Homomorphic Encryption), a novel selective encryption strategy that dynamically identifies and encrypts only the gradient components exceeding a DP-calibrated...

    arxiv.org/abs/2608.27108 · PDF

  5. 05

    PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact?

    Yitian Zhou, Jingyu Zheng, Qiliang Jiang, Linkang Du, Haoming Liu, Lichao Wu, Shiyi Zhao, Mengxiang Liu, Ruilong Deng

    cs.CR · cs.AI

    Industrial control systems (ICSs) rely on programmable logic controllers (PLCs) to connect networked computation with physical control. Tool-using large language model (LLM) agents represent an emerging attack threat: can an autonomous agent convert a network-reachable PLC into sustained adverse physical impact? However, existing evaluations focus on digital tasks or individual stages of PLC testing. In ICSs, evaluations that stop at software...

    arxiv.org/abs/2608.26882 · PDF

  6. 06

    Daydreaming: Stealing Hidden Agent Skills through Black-Box Task Interaction

    Yu-Lin Tsai, Yu-An Lu, Ci-Yang Tsai, Muxi Lyu, Raluca Ada Popa, Chia-Mu Yu

    cs.CR · cs.AI · cs.LG

    Agent skills bundle instructions, reference data, and executable helpers that let a general agent perform specialized tasks. Hosted providers can keep these files secret while selling access to task results, making the skill itself a valuable target. Existing disclosure defenses can block requests that ask for the skill or reproduce its text, but they cannot block customers from submitting the ordinary tasks the service is built to complete....

    arxiv.org/abs/2608.26733 · 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.