cs.CR · 2026-06-29 · No. 38

Cryptography and Security, 2026-06-29.

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

    Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models

    Yanchen Yin, Dongqi Han, Linghui Li

    cs.CR · cs.AI

    Jailbreak attacks bypass LLM safety alignment, yet their mechanisms remain poorly understood. We provide evidence that attacks do not comprehensively eliminate safety features, but instead selectively suppress specific attention heads. We identify two functionally differentiated types: Adversarially Compromised Heads (ACHs) concentrated in early layers, which are suppressed under attacks, and Safety-Aligned Heads (SAHs) in mid-layers, which...

    arxiv.org/abs/2606.28153 · PDF

  2. 02

    ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents

    Shijing Hu, Liang Liu, Zhu Meng, Zhicheng Zhao

    cs.CR · cs.AI

    Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments, and execute multi-step tasks. However, conventional function-calling benchmarks mainly evaluate task completion and API correctness, while privacy evaluation benchmarks typically focus on final responses or privacy judgments. Neither perspective captures purpose-bound information flow across...

    arxiv.org/abs/2606.28061 · PDF

  3. 03

    SHARD: cell-keyed residual splitting for alignment-resistant private dense retrieval

    Sergey Kurilenko

    cs.CR · cs.AI · cs.IR

    Dense embeddings underpin semantic search and RAG, yet a leaked vector store hands much of the underlying text back to whoever holds it. The attacks that make this possible (few-shot alignment, zero-shot inversion, unsupervised cross-space translation) share one weakness: the protected store is a single global geometry that can be aligned to a known one. A secret global rotation, the usual lightweight defence, is no exception: orthogonal...

    arxiv.org/abs/2606.27976 · PDF

  4. 04

    Agentic AI-Powered Re-Identification: An Emerging, Scalable Threat to Mobility Microdata Privacy

    Oscar Thees, Roman Müller, Matthias Templ

    cs.CR · cs.AI · stat.AP

    The widespread collection of fine-grained location data by commercial data brokers creates a re-identification risk that is not widely recognised by the public. While prior research has established that mobility traces are highly unique and that individuals can, in principle, be identified from a handful of spatio-temporal points, such attacks have historically required significant manual effort from skilled analysts, limiting their practical...

    arxiv.org/abs/2606.27936 · PDF

  5. 05

    Exploring and Exploiting Synchrony Limitations of Time-Triggered Network-Agnostic Guardians

    Shreya Vithal Kulhalli, Mohammad Ibrahim Alkoudsi, Gerhard Fohler

    cs.CR · cs.DC

    Time-triggered communication protocols rely on trusted components known as guardians to enforce adherence to predetermined network schedules. Network-agnostic guardians offer an efficient and scalable distributed solution with reduced implementation cost and complexity compared to network-aware alternatives. However, this efficiency is based on the guardian's dependence on the controlled node for clock synchronization, which introduces a...

    arxiv.org/abs/2606.27819 · PDF

  6. 06

    On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models

    Dewank Pant, Shruti Lohani, Avijit Kumar

    cs.CR · cs.AI · cs.LG

    Prompt injection is the top security risk for LLM-integrated applications, yet every defense proposed so far has been broken. We prove this is not a coincidence: in shared-embedding architectures that lack enforced control-data separation, perfect prompt-injection prevention is mathematically impossible. We formalize prompted systems as Prompted Action Models whose outputs include control-authoritative actions: refusal decisions, tool...

    arxiv.org/abs/2606.27567 · 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.