cs.CR · 2026-11-10 · No. 169
Cryptography and Security, 2026-11-10.
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-
01
DeepChronos: Temporal Neuro-Symbolic Reasoning for Multi-Step Attack Detection
Sofia Burkow, Andrea Agiollo, Enkeleda Bardhi, Fernando Kuipers, Kaitai Liang, Georgios Smaragdakis
cs.CR · cs.AI · cs.NI
Modern cyber threats commonly unfold as multi-step attacks comprising temporally and causally related phases. Current defenses commonly follow a detect first and correlate later paradigm. Intrusion detection systems classify events independently, while downstream systems reconstruct attack progression from the resulting alerts or audit records. In this context, learning-based detectors learn attack-step dependencies implicitly as statistical...
-
02
Double Blind Evals: Resolving the Dual Confidentiality Dilemma in AI Safety Auditing
Andrew Trask, Sol Messing, Vai Pahwa, Pegah Maham, Rene Kolga, Austin Frantz, Andrew Tash, Kate Thomas, Sean...
cs.CR · cs.AI · cs.LG
AI safety evaluations often involve sensitive prompts and proprietary models. Evaluators want to keep their evaluation prompts secret from model owners to prevent purposeful or incidental data leakage, ensuring longer usefulness of their benchmark. Model owners in turn wish to keep their proprietary model weights and inference code within their own secure infrastructure to protect their IP. We present a way forward for "double-blind evals",...
-
03
Say Shibboleth: Fingerprinting the LLMs and Harnesses Behind Agentic Attacks
Dario Pasquini, Reworr, Giuseppe Ateniese, Manish Bhatt, Sergej Epp
cs.CR · cs.AI
We study the fingerprinting of agentic cyberattacks. Our objective is to reliably infer information about the attacker's configuration, such as LLM version and harness, from telemetry. To achieve this, we introduce a technique we call shibboleth traps: modular honeypot services designed to elicit discriminative behaviors from agentic attackers. The traps make informative interactions a condition for obtaining resources the agent seeks,...
-
04
Lessons Not Learned: Why Cross-Chain Bridges Keep Losing Billions the Same Way
Mohsen Ahmadvand, Piotr Dobaczewski, Camille Bouzerand
cs.CR · cs.DC
Bridge hacks have cost billions, often without exploiting a code bug. In the cross-chain bridge hacks we catalogue from 2021 to 2026, failures of security posture, meaning how a bridge's people, code, controls and off-chain infrastructure are set up, account for 88% of reported losses since 2023, and nearly all repeat earlier failures. Code audits cannot catch these failures, so we propose a bridge security assessment rubric. It scores each...
-
05
GPU-Accelerated Non-Interactive Encrypted Neural Network Training with Batched Diagonal Packing
Kentaro Mihara
cs.CR · cs.LG
Training a neural network under homomorphic encryption requires transposes, batch reductions, optimizer updates, and repeated refreshes in addition to forward matrix products. We combine rectangular diagonal packing, feature-major SIMD mini-batch lanes, baby-step giant-step evaluation, and compact optimizer state in an MIT-licensed Rust CKKS implementation. Its CUDA path keeps training and bootstrap ciphertext arithmetic on the GPU, while...
-
06
FALC: An Artifact-Centric Life Cycle Model and Research Agenda for AI Forensics
Adrian Johannes Staeves, Mayur Rattan Jaisinghani, Rebekah Overdorf, Frank Breitinger
cs.CR · cs.LG
AI systems increasingly appear in criminal investigations as tools, targets, and sources of evidence, yet AI forensics lacks a systematic account of the artifacts they produce: investigators often do not know which traces to look for, and for many traces they do find, no established analysis technique exists. In this paper we first developed the Forensic AI Life Cycle (FALC) that unlike other life cycle models shifts the focus onto the...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.