cs.CR · 2026-10-05 · No. 134

Cryptography and Security, 2026-10-05.

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

    PoCoFL: POlicy-COmpliant Federated Learning

    Dominik Roy George, Varesh Mishra, Aysajan Abidin

    cs.CR · cs.LG

    Federated Learning (FL) is a privacy-oriented learning paradigm that enables collaborative model training while keeping training data local to participating clients. However, it does not guarantee that clients submit policy-compliant contributions or that aggregators process admitted contributions correctly. Existing verifiable FL systems tailor validation rules to specific FL settings, learning workflows, and cryptographic constructions,...

    arxiv.org/abs/2610.03650 · PDF

  2. 02

    Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks

    Neeraj Karamchandani, Piyush Nagasubramaniam, Xinhong Xie, Sencun Zhu, Dinghao Wu

    cs.CR · cs.AI · cs.LG

    Security benchmarks for LLM-based agents often report the attack success rate (ASR) as a measure of model robustness and use these scores to compare different models and defense mechanisms, assuming that they describe the security of the agent. In this paper, we explore whether it also influences the benchmark's measurement. To measure the effect of the benchmark representation, we introduce threat-preserving representation sensitivity...

    arxiv.org/abs/2610.03585 · PDF

  3. 03

    LiBRA: Detection-Aware Image Watermark Removal via Bidirectional Latent Optimization

    Saibo Ye, Huajie Chen, Xin Guo, Le Yang, Chi Liu, Xiangyu Hu, Jingjing Guo, Tianqing Zhu

    cs.CR · cs.AI

    Digital watermarking supports source attribution for AI-generated images, but its reliability depends on resistance to removal attacks. Some attacks attempt to remove watermarks by forcing the decoded watermark to differ from the original. However, this can produce an inverted watermark that remains detectable, causing removal to fail, while further attempts to alter the watermark may unnecessarily degrade image quality. To address these...

    arxiv.org/abs/2610.03166 · PDF

  4. 04

    EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents

    Shiyi Kuang, Xuemei Luo, Kun Liu, Junhai Li, Rui Tian, Feng Shi, Bo Shen, Nianyu Li, Dehui Li, Ping Chen

    cs.CR · cs.AI

    Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources. Existing benchmarks leave gaps in executable coverage of their runtime security risks, while evolving model capabilities, harnesses, tools, and threats motivate benchmark evolution. We introduce EvoRiskBench, an evolving benchmark organized around the EP-Path-EF framework, which links an...

    arxiv.org/abs/2610.03153 · PDF

  5. 05

    The Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMs

    Toluwani Aremu, Manit Baser, Mohan Gurusamy, Nils Lukas, Dinil Mon Divakaran

    cs.CR · cs.AI · cs.CL · cs.CY · cs.LG

    Open-weight language models can be downloaded, modified, and deployed beyond their developers' control, limiting the effectiveness of centrally enforced safeguards. Recent work has therefore proposed \emph{trigger-tag} mechanisms that produce a detectable signal when a model is used under a target condition, such as generating phishing contents. Although these mechanisms borrow from established techniques, their use for conditional misuse...

    arxiv.org/abs/2610.03124 · PDF

  6. 06

    Securing Computer-Use Agents Against Branch Steering Attacks

    Giulio Zingrillo, Hanna Foerster, Ilia Shumailov, Yiren Zhao, Robert Mullins

    cs.CR · cs.AI

    Modern Computer Use Agents (CUAs) directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect prompt injection across every rendered page and tool response. While the Dual-LLM pattern is the primary system-level architecture offering formal security guarantees - using an isolated Planner LLM (P-LLM) to fix execution paths before processing untrusted inputs via a Quarantined LLM (Q-LLM) - these...

    arxiv.org/abs/2610.03089 · PDF

  7. 07

    Beyond Predefined Sinks: Security-Aware Dependency Analysis for LLM Agents

    Hang Cui

    cs.CR · cs.AI

    Large language model (LLM)-based agents increasingly connect model-generated decisions to security-sensitive software capabilities such as command execution, filesystem access, network communication, browser control, and external tools. Existing analyses often use predefined sensitive operations as anchors, but operation identity alone is insufficient to determine security implications. We present AgentSecGraph, a security-aware static...

    arxiv.org/abs/2610.03014 · 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.