cs.CR · 2026-05-28 · No. 11

Cryptography and Security, 2026-05-28.

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

    Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests

    Richard J. Young, Gregory D. Moody

    cs.CR · cs.CL · cs.LG

    A general-purpose language model that answers a harmful question returns text; a coding model that complies with a malicious request can return a working weapon -- a keylogger, a ransomware stub, an exploit that runs as written. This asymmetry in the severity of a single act of compliance implies coding-specialized models should clear a higher refusal bar than general-purpose chat models, not a lower one, yet the field cannot presently tell...

    arxiv.org/abs/2605.28734 · PDF

  2. 02

    Blind PRNG Hijacking: An Undetectable Integrity-Preserving Attack Against LLM Watermarking

    Ziyang You, Huilong He, Xiaoke Yang, Xuxing Lu

    cs.CR · cs.AI

    Cryptographic watermarking is a leading defense for attributing text generated by large language models (LLMs). Existing schemes, including KGW, Unigram, and DipMark, derive their security guarantees from the assumption that the underlying pseudo-random number generator (PRNG) is trustworthy. This work introduces SeedHijack, the first supply-chain attack on LLM watermarking that is simultaneously (i) blind -- requiring no knowledge of the...

    arxiv.org/abs/2605.28632 · PDF

  3. 03

    Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation

    Jianwei Li, Jung-Eun Kim

    cs.CR · cs.AI · cs.LG

    This position paper argues that the AI/ML community should stop overclaiming and retire the label "positive backdoor," and instead treat trigger-activated hidden behaviors as Secret Alignment. Crucially, protective claims based on Secret Alignment should be presumed not secure by default unless supported by rigorous, standardized evaluation. The Private AI era, enabled by open-weight LLMs and accessible training/inference stacks, turns...

    arxiv.org/abs/2605.28597 · PDF

  4. 04

    Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

    Luca Beurer-Kellner, Aleksei Kudrinskii, Marco Milanta, Kristian Bonde Nielsen, Hemang Sarkar, Liran Tal

    cs.CR · cs.AI

    We analyzed 3,984 AI agent skills from major marketplaces and found 76 confirmed malicious payloads, including credential theft, backdoor installation, and data exfiltration. 13.4% of all skills contain at least one critical-level security issue and at least 8 manually confirmed malicious skills remain publicly available on clawhub.ai as of the date of publication. This report documents our methodology, presents a threat taxonomy based on...

    arxiv.org/abs/2605.28588 · 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.