cs.CR · 2026-08-21 · No. 91
Cryptography and Security, 2026-08-21.
4 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
4 entries-
01
TrustRAG: Blockchain-Enhanced RAG via Committee-Based Credibility Scoring
Baixiang Liu, Haotian Che, Yuan Li
cs.CR · cs.DC
Retrieval-Augmented Generation (RAG) lets Large Language Models (LLMs) pull in up-to-date, domain-specific information instead of relying only on what they were trained on. Yet most RAG systems still draw from centralized databases with limited oversight, making it difficult to verify where a document came from, whether it has been tampered with, or whether it should be trusted at all. This is a serious problem in domains where both the...
-
02
EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models
Yiting Qu, Ziqing Yang, Chi Cui, Ye Leng, Junjie Chu, Yang Zhang
cs.CR · cs.AI
Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet whether these hidden CoTs can be directly extracted from black-box models remains largely unexplored. In this work, we systematically study whether hidden CoTs can be extracted near-verbatim from black-box LRMs through API interactions. We identify a previously overlooked reasoning replay surface...
-
03
From Noise to Signal: Improving Security Log Anomaly Detection Using LLMs with Endpoint-Specific Logs
Christopher Henshaw, Gour Karmakar
cs.CR · cs.LG
Existing approaches to anomalous behaviour log detection, such as Wazuh rely primarily on predefined detection rules, while statistical anomaly detection approaches such as OpenSearch identify deviations from previously observed behavioural patterns. Recent research has investigated LLMs for log anomaly detection because of their ability to interpret semantic and contextual information. However, LLM-based approaches can be affected by prompt...
-
04
MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection
Yue Wang, Yi Liu, Gelei Deng, Ying Zhang, Yuekang Li, Zhenyu Chen, Leo Zhang
cs.CR · cs.AI
Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration. This creates a direct distribution channel for malicious behavior, yet existing malicious-Skill datasets are fragmented across sources, artifact formats, evidence regimes, and benign coverage; duplicated and structurally related content further complicates direct aggregation and evaluation. We present...
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.