cs.CR · 2026-09-10 · No. 111

Cryptography and Security, 2026-09-10.

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

    Learning Intrusion Response Strategies for OT Systems

    Duc Huy Le, Rolf Stadler

    cs.CR · cs.AI

    Cyberattacks against Operational Technology (OT) systems, which monitor and control industrial processes, pose an increasing threat to essential societal services. For this reason, developing automated intrusion response strategies is highly important. In this paper, we present a formal model of an OT intrusion response use case using the POMDP framework. It includes a realistic model of partial observability that is based on traffic...

    arxiv.org/abs/2609.10298 · PDF

  2. 02

    Maverick: Private and Verifiable LLM Inference Made Practical via Matrix-Vector Multiplication Delegation

    Ben Merbaum, Mohammad Amin Raeisi, Wenhao Wang, Charalampos Papamanthou, Katerina Sotiraki, Fan Zhang

    cs.CR · cs.LG

    Open-source large language models (LLMs) are increasingly competitive with closed-source models while offering transparency and the ability to run inference without exposing user inputs to a service provider. However, running large-scale models locally requires substantial computational resources. In practice, users may still resort to a third-party provider, giving rise to privacy and correctness concerns. Existing solutions that address...

    arxiv.org/abs/2609.10264 · PDF

  3. 03

    Decentralized network congestion control for DAG-based distributed ledger system

    Mayank Pandey, Rachit Agarwal, Sandeep Kumar Shukla, Nishchal Kumar Verma

    cs.CR · cs.DC · cs.NI

    We propose a variable and behavior-based node-specific proof-of-work (PoW) model for a directed acyclic graph (DAG)-based distributed ledger technology (DLT) network to mitigate decentralized network congestion control. Network congestion control for centralized communication systems is an established field of study, with detailed and continuous research being done on the subject. However, attention to congestion control in decentralized...

    arxiv.org/abs/2609.09961 · PDF

  4. 04

    Subgroup Membership Inference Audits of Differentially Private Synthetic Text

    Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar, Siew Kei Lam, Anil Anthony Bharath

    cs.CR · cs.AI

    Synthetic data releases are increasingly proposed in the literature as a means of sharing realistic data replicas in lieu of sensitive private datasets. Even when the worst-case privacy leakage of such releases is bounded by means of differential privacy (DP), in practice a residual risk remains. Membership inference attack (MIA) audits are conducted to empirically quantify this risk. However, existing methods only measure average-case risk...

    arxiv.org/abs/2609.09848 · PDF

  5. 05

    CS-Guard: Benchmarking LLM Guardrails for Code Generation Security

    Jinyang Li, Mingyu Guo, Hung X. Nguyen

    cs.CR · cs.AI

    Large language models (LLMs) have been ex- ploited to generate malware, but the effective- ness of guardrails for code generation secu- rity remains unclear. We introduce CS-Guard, the first benchmark to systematically evalu- ate guardrails for code generation security. It covers 1) text-to-code generation with 1000 high-quality malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack (FSA) that embeds malicious...

    arxiv.org/abs/2609.09798 · PDF

  6. 06

    How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE

    Yi Shi, Tanyu Chen, Kai Shen

    cs.CR · cs.AI · cs.CL · cs.LG

    Directional ablation removes an aligned language model's ability to refuse by projecting a single "refusal direction" out of the weights that write the residual stream. It needs no gradient-based training and no optimization, only a few hundred contrastive prompts, which makes it the canonical white-box attack on open-weight alignment. However, it has been established only on dense models up to roughly 70B parameters. We study whether it...

    arxiv.org/abs/2609.09793 · PDF

  7. 07

    Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning

    Thomas Rivasseau

    cs.CR · cs.AI

    Large language model safety and security research is preoccupied with, among other things, detecting and preventing jailbreak attacks: alignment bypasses that allow an adversarial user to elicit unwanted or harmful outputs from models. Arbitrary cipher, or covert communication, attacks are one such type of jailbreak and have previously been demonstrated against the fine-tuning APIs of commercial models. In these attacks, target models are...

    arxiv.org/abs/2609.09553 · 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.