cs.CR · 2026-08-18 · No. 88
Cryptography and Security, 2026-08-18.
8 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
8 entries-
01
Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis
Reza Fayyazi, Michael Zuzak, Shanchieh Jay Yang
cs.CR · cs.AI
Large Language Models (LLMs) are increasingly being deployed in cybersecurity operations to assist cybersecurity analysts with rapid decision-making against emerging threats. However, there is a main criteria that must be met when using LLMs in cybersecurity, that is, trust in the generated outputs. As Agentic AI is integrated into operational systems, a robust evidence attribution and provenance tracking technique is essential to trace the...
-
02
LLMs for Zero-Shot Threat Detection via Structured Risk Indicators
Abdullah Alghamdi, Siamak Layeghy, Marius Portmann
cs.CR · cs.LG · cs.NI
We propose a two-stage large language model (LLM) framework for zero-shot detection of insider threats and advanced persistent threats (APTs) from heterogeneous security logs. The framework models user activity as chronological timelines and incorporates retrieval-augmented generation (RAG) to provide personalised behavioural context from each user's historical activity. Rather than performing end-to-end classification directly from raw logs,...
-
03
Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs
Xiangfan Wu, Zonghao Ying, Huiyu Wu, Xing Zheng, Huangsheng Cheng, Xiaorong Shi, Jing Guo
cs.CR · cs.AI
As large language models become increasingly widespread, third-party providers that deploy open-weight models have become an important part of the ecosystem. Auditing the quality of their inference APIs is therefore an open problem. We formalize hosted model routing as a stochastic process and propose \mbox{\textbf{Ventor-QTest}}, a composite black-box audit that requires no probability information from the target API. Its repeated-request...
-
04
CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills
Mingxiao Liu, Zhoumian Jiang, Jianan Ma, Jian Zhang, Jialuo Chen, Xinhao Deng, Zhen Wang
cs.CR · cs.AI
Autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one at a time: a scanner returns a safety verdict for each skill and declares the ecosystem safe if every package passes. We show that this assumption fails under skill composition. A skill may pass the per-skill scanner individually yet participate in a risky composition when an agent connects its outputs, capabilities, or side effects with those...
-
05
Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles
Anik Jha
cs.CR · cs.LG
Trusted monitoring has a cheap, trusted model score a stronger untrusted model's actions, and a diverse ensemble of them beats a single stronger monitor at matched cost. They are built by minimising average pairwise correlation, and that paper's twelve monitors shared one base model, leaving open what supplies the diversity. We study 24 open-weight monitors spanning nine pretraining lineages and a 29x range of detection skill (pAUC at 10...
-
06
Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline
Mikhail Surikov
cs.CR · cs.AI · cs.SE
AI-assisted development tools generate vulnerable code at significant rates, yet few automated mechanisms exist to detect, enrich, fix, and verify security issues at development velocity, particularly ones that ground remediation in real-world threat context. This paper presents an automated security evaluation pipeline that generates Python code from LLMSecEval prompts, scans for vulnerabilities using CodeQL and Bandit in parallel with an...
-
07
Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm
Hidayet Aksu
cs.CR · cs.AI
Large language models (LLMs) are increasingly deployed as agents that operate equipment, execute instructions, and act inside institutional hierarchies, raising a question social psychology answered for humans six decades ago: how far will an agent escalate a harmful action when a legitimate authority insists? We port Milgram's obedience paradigm to LLMs as a standardized, fully scripted, replicable probe: the model plays the Teacher, a...
-
08
Digital Twin Degradation: Detecting Cyber Physical Attacks via Temporal Inconsistencies
Konstantinos E. Kampourakis, Vasileios Gkioulos, Sokratis Katsikas
cs.CR · cs.AI · cs.LG
Digital Twins (DTs) are increasingly used to monitor and analyze Cyber Physical Systems (CPS). However, in adversarial environments, the fidelity of a DT cannot be assumed. Communication delays, data manipulation, sensor degradation, or partial information loss may cause the DT state to diverge from the physical process it represents. Such divergence creates temporal inconsistencies that may reveal cyber physical attacks. This paper proposes...
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.