cs.CR · 2026-08-15 · No. 85

Cryptography and Security, 2026-08-15.

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

    Operationalizing Cyber Threat Intelligence with GraphRAG

    Atul Kabra, Prakhar Paliwal, Manjesh K. Hanawal

    cs.CR · cs.AI

    When a security researcher publishes a report on a cyberattack, detection engineers are supposed to turn it into working detection rules. In practice, most automated attempts at this only extract the simplest clues from the report --- bad IP addresses, domain names, and file hashes --- and turn them into block lists. This is a weak strategy, because attackers can change these simple clues within hours or days, so the resulting detections stop...

    arxiv.org/abs/2608.13050 · PDF

  2. 02

    Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents

    Jiajun Ruan, Peiyang Li, Yukun Chen, Fengting Li, Chao Feng

    cs.CR · cs.AI

    The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to mitigating these risks by integrating security mechanisms into the agent execution loop. However, existing runtime defenses rely heavily on manually designed interventions and lack a principled framework for their construction and maintenance. In this work, we first...

    arxiv.org/abs/2608.12977 · PDF

  3. 03

    Labels Are Not Endpoints: Treatment Leakage and Construct Validity in MCP Agent Security Evaluation

    Rana Muhammad Ahmed, Sabahat Abbas

    cs.CR · cs.AI

    Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution rows to 180 model-bound requests, 45 semantic requests, and 15 observable stimuli. Two schema treatments were delivered, but the planned external payload-family corpus was not. The historical grader exhibited direct treatment leakage: treatment metadata gated the ATTACK_SUCCESS class, so fixed...

    arxiv.org/abs/2608.12880 · PDF

  4. 04

    Discovering Persistent Behavioural Patterns for Interpretable Blockchain Forensics

    Dorottya Zelenyanszki, Zhe Hou, Kamanashis Biswas, Vallipuram Muthukkumarasamy

    cs.CR · cs.LG

    Public blockchain data enables large-scale DeFi-related analysis, but many existing approaches are application-specific, difficult to scale, or hard to interpret. This research proposes a scalable, application-agnostic framework for \emph{persistent behavioural pattern discovery} from large-scale blockchain activity. It constructs behaviour sentences enriched with contract, token and market context, then applies a two-step embedding process:...

    arxiv.org/abs/2608.12864 · PDF

  5. 05

    PIPES: Securing Agent Perception with Provenance and Priors

    Sanjay Kariyappa, Severin Klingler, G. Edward Suh

    cs.CR · cs.AI

    Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or what it should convey. We show that this gap enables state-corruption attacks, in which attacker-controlled content makes environmental claims beyond the informational authority of its response component and corrupts the agent's perceived environment, making the resulting action appear...

    arxiv.org/abs/2608.12789 · 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.