Cryptography and Security arXiv

Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models Eyal Hadad, Mordechai Guri arxiv.org/abs/2603.25403 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation Pei Chen, Geng Hong, Xinyi Wu, Mengying Wu, Zixuan Zhu, Mingxuan Liu, Baojun Liu, Mi Zhang, Min Yang arxiv.org/abs/2603.25500 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙸𝚁]

TAAC: A gate into Trustable Audio Affective Computing Xintao Hu, Feng-Qi Cui arxiv.org/abs/2603.25570 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙰𝙸]

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers Songyang Liu, Chaozhuo Li, Chenxu Wang, Jinyu Hou, Zejian Chen, Litian Zhang, Zheng Liu, Qiwei Ye, Yiming Hei, Xi Zhang, … arxiv.org/abs/2603.24414 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙰𝙸]

IPsec based on Quantum Key Distribution: Adapting non-3GPP access to 5G Networks to the Quantum Era Asier Atutxa, Ane Sanz, Eire Salegi, Gaizka González, Jasone Astorga, Eduardo Jacob arxiv.org/abs/2603.24426 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙽𝙸]

Analysing the Safety Pitfalls of Steering Vectors Yuxiao Li, Alina Fastowski, Efstratios Zaradoukas, Bardh Prenkaj, Gjergji Kasneci arxiv.org/abs/2603.24543 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙲𝙻]

Infrastructure for Valuable, Tradable, and Verifiable Agent Memory Mengyuan Li, Lei Gao, Haoxuan Xu, Jiate Li, Potung Yu, Lingke Cheng, Yue Zhao, Murali Annavaram arxiv.org/abs/2603.24564 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙲𝚈]

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search Hyomin Lee, Sangwoo Park, Yumin Choi, Sohyun An, Seanie Lee, Sung Ju Hwang arxiv.org/abs/2603.22341 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻]

Q-AGNN: Quantum-Enhanced Attentive Graph Neural Network for Intrusion Detection Devashish Chaudhary, Sutharshan Rajasegarar, Shiva Raj Pokhrel arxiv.org/abs/2603.22365 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

mmFHE: mmWave Sensing with End-to-End Fully Homomorphic Encryption Tanvir Ahmed, Yixuan Gao, Adnan Armouti, Rajalakshmi Nandakumar arxiv.org/abs/2603.22437 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙻𝙶 𝚎𝚎𝚜𝚜.𝚂𝙿]

Architecture-Derived CBOMs for Cryptographic Migration: A Security-Aware Architecture Tradeoff Method Eduard Hirsch, Kristina Raab arxiv.org/abs/2603.22442 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝚂𝙴]

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning Charoes Huang, Xin Huang, Ngoc Phu Tran, Amin Milani Fard arxiv.org/abs/2603.22489 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝚂𝙴]

OrgForge-IT: A Verifiable Synthetic Benchmark for LLM-Based Insider Threat Detection Jeffrey Flynt arxiv.org/abs/2603.22499 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙻𝙶]

CTF as a Service: A reproducible and scalable infrastructure for cybersecurity training Carlos Jimeno Miguel amd Mikel Izal Azcarate arxiv.org/abs/2603.22511 [𝚌𝚜.𝙲𝚁]

STRIATUM-CTF: A Protocol-Driven Agentic Framework for General-Purpose CTF Solving James Hugglestone, Samuel Jacob Chacko, Dawson Stoller, Ryan Schmidt, Xiuwen Liu arxiv.org/abs/2603.22577 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙼𝙰]

Semi-Automated Threat Modeling of Cloud-Based Systems Through Extracting Software Architecture from Configuration and Network Flow Nicholas Pecka, Lotfi Ben Othmane, Bharat Bhargava, Renee Bryce arxiv.org/abs/2603.22603 [𝚌𝚜.𝙲𝚁]

BioShield: A Context-Aware Firewall for Securing Bio-LLMs Protiva Das, Sovon Chakraborty, Sidhant Narula, Lucas Potter, Xavier-Lewis Palmer, Pratip Rana, Daniel Takabi, Mohammad Ghasemigol arxiv.org/abs/2603.22612 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙷𝙲]

BlindMarket: Enabling Verifiable, Confidential, and Traceable IP Core Distribution in Zero-Trust Settings Zhaoxiang Liu, Samuel Judson, Raj Dutta, Mark Santolucito, Xiaolong Guo, Ning Luo arxiv.org/abs/2603.22685 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙻𝙾]

Does Teaming-Up LLMs Improve Secure Code Generation? A Comprehensive Evaluation with Multi-LLMSecCodeEval Bushra Sabir, Shigang Liu, Seung Ick Jang, Sharif Abuadbba, Yansong Gao, Kristen Moore, SangCheol Kim, Hyoungshick Kim, … arxiv.org/abs/2603.22717 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝚂𝙴]

CIPL: A Target-Independent Framework for Channel-Inversion Privacy Leakage in Agents Tao Huang, Chen Hou, Jiayang Meng arxiv.org/abs/2603.22751 [𝚌𝚜.𝙲𝚁]