cs.CR · 2026-10-30 · No. 158

Cryptography and Security, 2026-10-30.

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

01 — The papers

6 entries
  1. 01

    TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races

    Tom Sander, Pierre Fernandez, Itai Gat, Haiming Bao, Jiaxin Shi, Jason Park, Valeriu Lacatusu, Sylvestre-Alvise...

    cs.CR · cs.AI · cs.CL

    We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative decoding: tokens that replace rejected drafts remain watermarked with the same keys, and the acceptance rate is unchanged. It also preserves output diversity and adds no measurable inference latency. Its predecessor, TextSeal, restores diversity in the Gumbel-max scheme by routing each token to one of two keys via a coin flip....

    arxiv.org/abs/2610.40613 · PDF

  2. 02

    Power Adjusting Games Under Block-Dependent Pool Payout Schemes

    Mustafa Doger, Sennur Ulukus

    cs.CR · cs.DC · cs.IT · math.PR

    Advanced power adjusting block withholding attacks such as PAW and T-PAW have been analyzed so far under a global-reset version of the proportional scheme (GRP), which is rarely used in practice. In this paper, we analyze T-PAW, which contains FAW and PAW as special cases, under the block-dependent payout schemes deployed in practice: Pay-Per-Last-N-Shares (PPLNS), round-based Proportional (PROP) and exponential-decay (EXP). We derive the...

    arxiv.org/abs/2610.40558 · PDF

  3. 03

    Deep Learning Based Behavioral Drift Modeling for Continuous Biometric Authentication

    Suprava Saha Dibya, Minar, Abdulla Al Noman, Md. Zafir Abid Shresto, Ahmed Sayef

    cs.CR · cs.HC · cs.LG

    This research proposes a two-level keystroke dynamics authentication system that provides defense-in-depth security through continuous behavioral drift monitoring. Level 1 employs fixed-text password authentication using Temporal Convolutional Networks (TCN) with contrastive learning and population-based training (PBT), achieving 3.77% EER for high-security login verification. Upon successful authentication, Level 2 continuously monitors user...

    arxiv.org/abs/2610.40398 · PDF

  4. 04

    Understanding and Mitigating Role Spoofing in LLMs

    Ezra Edelman, Benjamin Edelman, Surbhi Goel, Eran Malach

    cs.CR · cs.AI

    Despite growing capabilities, LLMs remain susceptible to prompt injections: malicious inputs that can manipulate or hijack models. In particular, it has recently been observed that LLMs can exhibit role confusion (Ye et al., 2026), where models attribute the source of text based on its style instead of its labeled role. Malicious text in tool outputs (for instance, a malicious webpage accessed by an agent) can leverage role confusion to...

    arxiv.org/abs/2610.40396 · PDF

  5. 05

    DYNAS: A Dynamic Network Penetration Testing Framework Using Deep Hierarchical Reinforcement Learning

    Md. Rakibul Hassan, Majedul Islam, Md. Ashraful Alam, Muhammad Iqbal Hossain, Swakkhar Shatabda

    cs.CR · cs.LG · cs.NI

    As network scale and uncertainty complicate automated penetration testing, reinforcement learning (RL) environments must support controlled evaluation under defensive and non-stationary conditions. We present DYNAS (Dynamic Network Attack Simulator), which combines parameterized large-scale scenario generation with stateful intrusion detection responses, explicit scan false-positive and false-negative noise, temporary service unavailability,...

    arxiv.org/abs/2610.40214 · PDF

  6. 06

    InferD: A Honeypot Framework for AI Inference Infrastructure

    Hicham Hammouchi, Gabriele Lenzini

    cs.CR · cs.AI

    Large language model serving stacks, commercial inference APIs, vector databases, and agent orchestration gateways are now ex- posed on the public internet and indexed by commodity scanners within hours of deployment. The threat characteristics of this sur- face are only beginning to be measured, and the honeypot frame- works that could measure it were designed for conventional net- work services rather than for AI infrastructure. In fact,...

    arxiv.org/abs/2610.39807 · 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.