cs.CR · 2026-08-10 · No. 80

Cryptography and Security, 2026-08-10.

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

    Soft Redaction of Image Provenance via Zero-Knowledge Proofs

    Muhammad Awan, John Collomosse

    cs.CR · cs.AI

    Content provenance standards, such as C2PA, are increasingly used to attach signed records of origin, editing history, and rights to digital images. However, provenance transparency can conflict with privacy -- assertions that strengthen trust in an image may also reveal sensitive information about the creator or capture context. We propose soft redaction for image provenance: a mechanism that replaces sensitive provenance assertions with...

    arxiv.org/abs/2608.07063 · PDF

  2. 02

    HarnessSafe: Evaluating Safety Across Persistent Carriers in Agent Harnesses

    Xiao Zhang, Yusheng Wang, Yuhao Fei, Dongyuan Li, Zian Liang, Liuyu Xiang, Hongxun Gu, Zhaofeng He

    cs.CR · cs.AI

    Modern agent harnesses persist state across tasks and sessions through persistent carriers like memory, skills, tools, and shared artifacts. However, this capability creates delayed safety risks: attacker-influenced content can cross system boundaries and later affect the execution of a benign request. Existing benchmarks typically focus on a few carriers or harnesses, while end-to-end attack-success rates reveal little about how risks...

    arxiv.org/abs/2608.06984 · PDF

  3. 03

    LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes

    Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo, Kaichen Yang

    cs.CR · cs.AI · cs.CL

    Low-rank adaptation (LoRA) enables efficient specialization and distribution of large language models through compact adapters. However, untrusted adapters introduce a supply-chain threat: a backdoored adapter can cause a model to generate harmful content, malicious code, political propaganda, or covert advertisements when an input contains a hidden trigger. Adapter-agnostic defenses merge the adapter with the base model, which dilutes...

    arxiv.org/abs/2608.06795 · 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.