cs.CR · 2026-11-05 · No. 164

Cryptography and Security, 2026-11-05.

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

01 — The papers

7 entries
  1. 01

    Signed, Sealed, Leaked: Trust Beyond Signature for MCP Toolchains

    Yichiet Aun, Mohammed A. Alhartomi, Jing Jie Tan, Waqas Nadeem, Adeb Salh, Shankar Karuppayah, Sin Chee Tan

    cs.CR · cs.AI · cs.MA

    AI agents rely on third-party tools, such as Model Context Protocol (MCP) servers, whose publishers can be authenticated and whose execution can be restricted by runtime security policies. Yet authenticity does not guarantee benign behaviour: a legitimately signed tool may perform its advertised function while concealing malicious code that leaks confidential information. We demonstrate this trust failure with a signed MCP tool that embeds...

    arxiv.org/abs/2611.06585 · PDF

  2. 02

    Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation

    Georgios Feretzakis, Alexandros Papaspyridis

    cs.CR · cs.IR · cs.LG

    Offline retrieval-augmented generation (RAG) on edge devices is updated through signed knowledge packs that carry text and precomputed embedding vectors. A signature proves who published a pack, not that its vectors encode its text. We study this text-vector integrity gap. A verifier that recomputes vectors and accepts them within a cosine tolerance concedes a predictable share of queries to an attacker who controls the vectors: the hijack...

    arxiv.org/abs/2611.06498 · PDF

  3. 03

    CoRTeC: A Differentially Private Release for Synthetic Tabular Data, Decodable by Any Generator

    Calister Nnona

    cs.CR · cs.LG

    The records that could train the most useful models, such as a hospital's patient files, are often the ones an institution cannot share. We propose CoRTeC, a method that releases synthetic versions of such records under differential privacy. Differential privacy places a proven limit on what the synthetic data can reveal about any person, and in particular on membership inference. CoRTeC spends the privacy budget once, on a small file of...

    arxiv.org/abs/2611.06342 · PDF

  4. 04

    A.S.E 2.0: Understanding How Repository Context Impacts the Security of LLM-Generated Code

    Jiongchi Yu, Keke Lian, Junqing Wang, Zhikang Fan, Zhaoxuan Li, Yongheng Huang, Ziming Zhao, Dong Zhang

    cs.CR · cs.AI · cs.SE

    Large language model (LLM) coding assistants and agents construct a repository context before generating code. For security-sensitive code, this context decides whether the model sees the project's safeguards (e.g., authorization checks) or insecure code to imitate. However, context construction is designed almost exclusively for functional correctness, and secure-code benchmarks treat the context as fixed, so how repository context affects...

    arxiv.org/abs/2611.06294 · PDF

  5. 05

    Analysis of Local Open-Weight LLM Agents on Vulnerability-Reproduction Tasks

    Jorge García-Carrasco, Javier Sanchis, Álvaro Navarro, Alejandro Maté, Juan Trujillo

    cs.CR · cs.LG · cs.SE

    Open-weight language models that fit on a single consumer GPU are becoming capable on a growing range of tasks, and they matter because they can run locally without sending the code to a hosted service. Vulnerability reproduction, turning a vulnerability description into an input that crashes the vulnerable build, is a natural target for them, since it is an automated analysis task closer to test generation than to code comprehension and it...

    arxiv.org/abs/2611.06257 · PDF

  6. 06

    Network Intrusion Forensic Detection System with Explainable Artificial Intelligence and Digital Chain of Custody

    Jose Luis Vela Alonso, Carmen Pellicer

    cs.CR · cs.LG

    Deploying an explainable intrusion detection model from a validated laboratory setting into a forensic workflow requires guarantees that benchmarks do not test: that the certified model is the exact artifact applied to a case, that heterogeneous evidence can be classified reliably, and that every step is verifiable. We present MODEXRE, a forensic pipeline that extends a previously validated synthetic-data-trained XGBoost classifier with SHAP...

    arxiv.org/abs/2611.06173 · PDF

  7. 07

    Reconciling Privacy with Provenance for Language Model Watermarks

    Elise L. Han, Tatsunori Hashimoto

    cs.CR · cs.AI · cs.CL

    Watermarking has great potential for regulating the use of language models (LMs), but its deployment has been marred by controversy, as many users argue that fine-grained tracking of LM usage violates their privacy. This tension reduces the effectiveness of watermarks, as users engage in evasion strategies such as paraphrasing that can remove much of the watermark signal. We show that provenance and privacy can be reconciled if we shift the...

    arxiv.org/abs/2611.06100 · 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.