cs.CR · 2026-08-25 · No. 95

Cryptography and Security, 2026-08-25.

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

    Robustness of Anomaly Detection Models for Industrial Control Systems under Training-Time Data Contamination

    Mustafa Umut Ozbek, Taiwo Ojo, Pooria Madani, Khalil El-Khatib, Li Yang

    cs.CR · cs.LG

    Machine-learning-based anomaly detection is increasingly used in industrial control systems (ICS), yet most studies assume that detector training data is trustworthy. In practice, training data may be corrupted through compromised logs, labeling errors, manipulated historian records, or unsafe retraining processes. This paper evaluates the robustness of offline ICS anomaly-detection pipelines on the Secure Water Treatment (SWaT) benchmark...

    arxiv.org/abs/2608.23547 · PDF

  2. 02

    Adapter-Based Few-Shot Continual Learning for Malicious Packet Recognition

    Kyle Stein, Guillermo Francia, III Eman El-Sheikh, Andrew Arash Mahyari

    cs.CR · cs.AI

    The continual evolution of malware variants necessitates detection systems that can adapt to new threats without retraining from scratch. However, continually updating models on new data often leads to catastrophic forgetting, where previously learned knowledge is overwritten. While continual learning has been increasingly explored for malware detection, the specific setting of Few-Shot Class-Incremental Learning (FSCIL), where new malware...

    arxiv.org/abs/2608.23536 · PDF

  3. 03

    InjecMEM: Memory Injection Attack on LLM Agent Memory Systems

    Hanling Tian, Gengyu Zhang, Zeyang Sha, Jingying Wang, Yuhang Liu, Zhehao Huang, Kun Yang, Xiaolin Huang

    cs.CR · cs.AI

    Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question: will memory system introduce new vulnerabilities into agents? Thus we propose InjecMEM, a novel memory injection attack paradigm that requires only a single interaction (no read/edit access to memory store) to steer later responses of related queries toward a pre-specified output. Guided by the...

    arxiv.org/abs/2608.23471 · PDF

  4. 04

    Adversarial Entropy Inflation Against Gumbel-Based Inference Verification

    Nikita Kezins

    cs.CR · cs.AI

    Gumbel-based inference verification bounds LLM weight exfiltration by only forgiving token choices that plausibly arise from honest GPU nondeterminism, reporting a >200x slowdown for a steganographic adversary under benign prompt traffic. This bound assumes a passive attacker; we show it degrades sharply against an adversary who instead controls the prompt distribution. Because the verifier's admissible-token-set size is driven by the model's...

    arxiv.org/abs/2608.23375 · PDF

  5. 05

    FIDES: A Concordance Protocol for LLM-Generated Trading Strategies

    Arther Tian, Alex Ding, Simon Wu, Aaron Chan

    cs.CR · cs.AI

    An LLM asked for a trading strategy returns three artifacts at once: a natural-language rationale, an executable implementation, and once run, a track record. Whether these are the same object is rarely checked. We present FIDES, a measurement protocol that treats them as three views to be reconciled rather than one deliverable to be graded. Through dual delivery, a single model call returns both a natural-language strategy with an explicit...

    arxiv.org/abs/2608.23308 · 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.