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-
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...
-
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...
-
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...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.