cs.CR · 2026-07-15 · No. 54

Cryptography and Security, 2026-07-15.

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

01 — The papers

3 entries
  1. 01

    Watermark Forensics for Generative Models: An Information-Theoretic Perspective

    Xiaoyu Li, Zheng Gao, Xiaoyan Feng, Jiaojiao Jiang, Yulei Sui, Jiankun Hu

    cs.CR · cs.IT · cs.LG

    A watermark in a generative model's output is usually asked only whether a text is machine-made. The same mark can do more: attribute it to the user who produced it, extract a hidden payload, or localize the part that survives editing. These form a forensic ladder, and we ask what each rung costs in the sample length $n$. One object organizes the answers. Let $S$ be the secret the mark carries (a user's identity or payload), and let the...

    arxiv.org/abs/2607.13003 · PDF

  2. 02

    Silent Alarm: A J-Space Protocol for Comparing Danger Recognition Across Models and Quantization Levels

    Roman Prosvirnin, Victor Minchenkov, Alexey Soldatov, Vladimir Bashun

    cs.CR · cs.AI

    Jailbreak-robustness research typically evaluates safety through generated responses using an LLM-as-judge approach. Such evaluations, however, are sensitive to the benchmark's grading procedure and capture only observed behavior on a given set of attacks, without directly revealing the hidden fragility of the underlying safety mechanisms. This work proposes JADR (Jacobian Assessment of Danger Recognition), a protocol that measures a model's...

    arxiv.org/abs/2607.12792 · PDF

  3. 03

    Bulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities

    Qiyuan Fan, Zhi Li, Junjie Li, XiaoFeng Wang, Bin Yuan, Deqing Zou

    cs.CR · cs.AI · cs.SE

    Filesystem isolation in container ecosystems is often weakened by cross-boundary path misresolution, causing path traversal (PaTra) vulnerabilities. These vulnerabilities stem from insecure host-container interactions and have become increasingly pervasive as cloud systems mount shared resources, such as GPUs and agent workspaces, into containers to support AI workloads. Existing defenses remain inadequate. Kernel-level protections are...

    arxiv.org/abs/2607.12723 · 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.