cs.CR · 2026-09-28 · No. 127

Cryptography and Security, 2026-09-28.

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

    AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents

    Weida Liang, Shi Qiu, Zhun Wang, Simon Sure, Xiaoyuan Liu, Tianneng Shi, Zhaorun Chen, Wenbo Guo, Dawn Song

    cs.CR · cs.AI

    AI agents combine language models with external data and tools that can modify files, call APIs, or execute code. Security failures can arise when adversarial content changes an agent's tool use or when the surrounding software contains vulnerabilities such as path traversal or command injection. We study authorized white-box pre-deployment auditing, where the auditor has access to the target repository and a controlled runtime, but...

    arxiv.org/abs/2609.31318 · PDF

  2. 02

    Resource-Optimized and Energy-Aware Agentic AI Framework Anchored on Blockchain for Secure Software Supply Chains

    Toqeer Ali Syed, Asadullah Abdullah Khan

    cs.CR · cs.AI

    This paper proposes a blockchain-backed agentic security framework designed to safeguard the complete software development lifecycle (SDLC) while also securing the agentic AI components responsible for monitoring it. The framework coordinates a set of specialised security agents, covering source integrity, dependency and SBOM analysis, CI configura tion auditing, artifact verification, and runtime policy evaluation, each supported by a large...

    arxiv.org/abs/2609.31282 · PDF

  3. 03

    Deduplication-while-Training: A Resilient Paradigm for Privacy-Preserving Cross-Client Deduplication in Federated Learning

    Rongxi Wang, Guanxiong Ha, Chunfu Jia, Yongsheng Lin, Minfen Gao, Hanmiaomiao Wang

    cs.CR · cs.DC

    Cross-client duplicate data in large language model training corpora degrades the efficiency of federated learning (FL) while exacerbating model memorization and privacy risks. Privacy-preserving cross-client deduplication effectively mitigates this issue by eliminating duplicate training data. However, existing schemes all follow a "Deduplication-before-Training" paradigm. This serially coupled paradigm incurs high fault-tolerance costs and...

    arxiv.org/abs/2609.31262 · PDF

  4. 04

    JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models

    Jianyi Hu, Hangtao Zhang, Yi Liu, Yeqi Zeng, Li Zeng, Xianlong Wang, Rui Wang, Leo Yu Zhang

    cs.CR · cs.AI · cs.CL

    Models trained with reinforcement learning for calibrated decisions (RLCD), such as Jev, answer a typed question about an input, the state, with a probability, a choice, or a score, and software acts on the answer without a person reading it. Their robustness has not been measured: adversarial benchmarks score what a model generates or executes, whereas a typed model generates nothing and returns a well-formed answer even when manipulated....

    arxiv.org/abs/2609.31142 · PDF

  5. 05

    Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance

    Kai Yao

    cs.CR · cs.AI · cs.CV · cs.LG

    Passive image provenance asks whether pixels alone can reveal where an image came from: a human, an aggregate AI class, or a particular generator. This becomes a robustness problem once a source image can be edited before the verifier sees it. We study the problem as source--target verification under adversarial distribution shift. Our first result gives the exact best-case limit for any image-only verifier: the largest robust...

    arxiv.org/abs/2609.30997 · 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.