cs.CR · 2026-08-27 · No. 97

Cryptography and Security, 2026-08-27.

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

    EVOMAL: Self-Poisoning in Self-Evolving Coding Agents

    Xiaodong Wu, Yu Shi, Qi Li, Zhimin Zhao, Xiangman Li, Bram Adams, Ahmed E. Hassan, Jianbing Ni

    cs.CR · cs.AI

    Self-evolving LLM coding agents write their own tools by imitating retrieved skills from shared skill libraries. We identify a vulnerability in this loop: during authoring, a retrieved malicious skill can become the template for a new skill that preserves the payload. We call this self-poisoning: the agent authors, stores, and runs the resulting malicious skill. We exploit it through EvoMal, an attack that amplifies self-poisoning by wrapping...

    arxiv.org/abs/2608.25776 · PDF

  2. 02

    MeMark: Membrane-Space Watermarking for Spiking Neural Networks

    Roberto Riaño, Gorka Abad, Stjepan Picek, Aitor Urbieta

    cs.CR · cs.AI · cs.LG

    Spiking Neural Networks (SNNs) are increasingly distributed as pretrained checkpoints and reused as backbones for new tasks. However, current SNN watermarks are mainly verified against the model output. Thus, a user who replaces the output head can keep most of the original network while removing the evidence used for verification. We present MeMark, a watermark designed for the checkpoint-reuse setting. Instead of storing the watermark in...

    arxiv.org/abs/2608.25738 · PDF

  3. 03

    Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale

    Peichun Hua, Danyang Chen, Junan Zhang, Haifeng Sun, Jingyu Wang, Diwen Xue, Mingyu Li, Yunming Xiao

    cs.CR · cs.AI · cs.IR · cs.LG

    Hosted retrieval-augmented generation (RAG) and semantic search allow users to query valuable provider-held corpora, raising two competing demands: to hide each query and chosen result, yet reveal only the documents that the user is authorized to receive. Existing cryptographic approaches either make this costly by processing the entire corpus for every query, or sacrifice quality for efficiency by scanning a few clusters. We repurpose...

    arxiv.org/abs/2608.25735 · PDF

  4. 04

    AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation

    Junchen Ding, Jialiang Dong, Yichen Zhu, Yi Liu, Gelei Deng, Willy Susilo, Siqi Ma, Yuekang Li

    cs.CR · cs.AI

    The integration of Large Language Models (LLMs) into cybersecurity has transformed vulnerability assessment, but it has also produced a trustworthiness crisis driven by the unchecked proliferation of "AI slop." These artifacts, hallucinated vulnerabilities, plausible but incorrect patches, and semantically repackaged bug reports, impose a cognitive burden on human triage pipelines that mirrors a denial-of-service attack. This paper surveys...

    arxiv.org/abs/2608.25667 · PDF

  5. 05

    MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak Vulnerabilities

    Tianshi Wang, Jingsong Wang, Yafei Huang, Fengling Li, Xin Li, Lei Zhu

    cs.CR · cs.AI · cs.MM

    Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet how different factors shape their jailbreak vulnerabilities remains poorly understood. Existing benchmarks often couple harmful intent, prompt framing, visual semantics, and instruction carrier within individual jailbreak instances, obscuring the specific sources of observed vulnerabilities. To address this limitation, we introduce MMJailBench,...

    arxiv.org/abs/2608.25490 · PDF

  6. 06

    MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration

    Miseon Yu, Jaehoon Choi, Younghan Lee, Yunheung Paek

    cs.CR · cs.AI · cs.MA

    Despite their strong ability to generate code, large language models often fail to produce secure code, as their outputs frequently contain security vulnerabilities. Secure code generation is inherently challenging because it requires solving a multi-objective problem: functional correctness and security. Existing approaches address this challenge by injecting external security knowledge or by using agentic feedback and iterative refinement....

    arxiv.org/abs/2608.25457 · PDF

  7. 07

    LLMscope: Extracting LLM Assets from Edge AI Chips via Optical Probing

    Dev Mehta, Lily Dukette, William Folan, Olivia Kochol, Noah Solomon, Shahin Tajik, Fatemeh Ganji

    cs.CR · cs.AI

    The move of LLM inference to edge AI accelerators introduces new physical vulnerabilities. During execution, model parameters and intermediate inference states are repeatedly loaded into and processed on the chip, making them suscep- tible to physical side-channel attacks. In this work, by deploying laser voltage imaging, we show that one can extract LLM assets during inference, namely embeddings, attention, and quantized MLP weights,...

    arxiv.org/abs/2608.25321 · 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.