cs.CR · 2026-07-31 · No. 70

Cryptography and Security, 2026-07-31.

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

01 — The papers

5 entries
  1. 01

    Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation

    Fazhong Liu, Zhuoyan Chen, Haozhen Tan, Yan Meng, Guoxing Chen, Haojin Zhu

    cs.CR · cs.AI

    World models give embodied AI a predictive core: they compress observations into states, simulate action-conditioned futures, and enable planning beyond reactive control. This predictive layer, however, opens a new security boundary-compromise can propagate from data, sensors, prompts, or feedback into physical action. Rather than treating world models as an isolated component, this survey traces threats across their entire lifecycle-from...

    arxiv.org/abs/2607.28226 · PDF

  2. 02

    Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Data

    Pouya Rajabi, Mohsen Toorani

    cs.CR · cs.DC · cs.LG

    Federated learning enables multiple institutions to train shared models without exchanging raw clinical EEG data, but it does not fully prevent privacy leakage from individual model updates. This paper presents a privacy-preserving federated learning framework for clinical EEG data using masking-based secure aggregation as the core protection mechanism. The framework combines graph-based communication, threshold secret sharing,...

    arxiv.org/abs/2607.28191 · PDF

  3. 03

    Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs

    Roberto Riaño, Gorka Abad, Stjepan Picek, Aitor Urbieta

    cs.CR · cs.AI

    Backdoor attacks on Spiking Neural Networks (SNNs) have primarily assumed dirty-label poisoning, in which triggered training samples are relabeled to an attacker-selected class. We study clean-label temporal poisoning, where a fixed timestamp transformation is applied only to the target-class training streams, leaving their labels unchanged. The transformation preserves the per-pixel, per-polarity event count exactly, making clean and...

    arxiv.org/abs/2607.28075 · PDF

  4. 04

    Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks

    Spyridon Raptis, Haralampos-G. Stratigopoulos

    cs.CR · cs.AI · cs.LG

    Spiking Neural Networks (SNNs) communicate through sparse binary spike events rather than dense activations, enabling energy-efficient inference on neuromorphic hardware and motivating their use in always-on, battery-powered edge systems. We show that this same efficiency advantage creates a distinct security risk: sponge attacks can increase inference-time spike activity and synaptic workload, inflating energy consumption while remaining...

    arxiv.org/abs/2607.27990 · PDF

  5. 05

    Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs

    Pingyu Wu, Lingyao Zhu, Weiming Zhang, Nenghai Yu

    cs.CR · cs.AI

    Large language model safeguards decide whether to answer before seeing how an answer will be used. This creates a basic problem for dual-use tasks: the same answer can help an authorized professional or an attacker, while an attacker can imitate a benign request and interaction history. We separate the capability released by the model from the evidence available about downstream use. When that evidence is copyable, we derive the exact...

    arxiv.org/abs/2607.27951 · 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.