iiinova — where your digital self keeps evolving

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Abbas Raftari: From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents arxiv.org/abs/2610.12463 arxiv.org/pdf/2610.12463 arxiv.org/html/2610.12463

010

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Shihab Ahmed, Md Sajidul Islam Sajid, Teryl Taylor, Frederico Araujo, Tariqul Islam: ORCAGen: Orchestrating Context-Aware Malware Deception with RAG-Guided Generative AI arxiv.org/abs/2610.12415 arxiv.org/pdf/2610.12415 arxiv.org/html/2610.12415

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Zheng, Zhang, Zhang, Zhang, Zhang, Sun, Zhang, He, Chua, Hu, Zhou, Lu, Wang: ReSI: Recursive Safety Improvement toward Resistant and Resilient AI arxiv.org/abs/2610.12233 arxiv.org/pdf/2610.12233 arxiv.org/html/2610.12233

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Pranay Anchuri, Ben Berger, Matteo Campanelli, Akaki Mamageishvili: One Node, Two Roles: Simultaneous Contests for Validation and Attention in Rollups arxiv.org/abs/2610.12220 arxiv.org/pdf/2610.12220 arxiv.org/html/2610.12220

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Georgios Milis, Tom Sander, Tom\'a\v{s} Sou\v{c}ek, Heng Huang, Pierre Fernandez: Could LLM Watermark Detection be Public? arxiv.org/abs/2610.12106 arxiv.org/pdf/2610.12106 arxiv.org/html/2610.12106

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Friedrich Vandenberghe, Lachlan Gunn, Bruno Volckaert, Merlijn Sebrechts: Protecting CPU AI On Edge TEEs: WebAssembly's Promise and Practical Challenges arxiv.org/abs/2610.12050 arxiv.org/pdf/2610.12050 arxiv.org/html/2610.12050

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Khiem Pham-Tuan, Minh Quang Le, Khuong Nguyen-An: HPQ-AKE: A Provably Secure Sign-Less Hybrid Authenticated Key Exchange Protocol for Bandwidth-Constrained IoT and Edge Networks arxiv.org/abs/2610.12024 arxiv.org/pdf/2610.12024 arxiv.org/html/2610.12024

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Roland Plaka, Mikael Asplund, Simin Nadjm-Tehran: Moving Target Defense in SDN-enabled EV Charging Network arxiv.org/abs/2610.11996 arxiv.org/pdf/2610.11996 arxiv.org/html/2610.11996

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Qi Liu, Geng Hong, Xinyang Zhang, Pei Chen, Yutong Li, Min Yang: From Public Posts to AI-Search Citations: Measuring the Fragility of AI Search arxiv.org/abs/2610.11932 arxiv.org/pdf/2610.11932 arxiv.org/html/2610.11932

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Steve Nouyep, S\'ebastien Salva, Maxime Puys: A Security Meta-Model for Retrieval-Augmented Generation Systems arxiv.org/abs/2610.11893 arxiv.org/pdf/2610.11893 arxiv.org/html/2610.11893

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Mukta Debnath, Krishnendu Guha, Debasri Saha, Amlan Chakrabarti, Susmita Sur-Kolay: Secure Aggregate Encryption with Identity-Based Authentication for Multi-Vendor FPGA Cloud Deployment arxiv.org/abs/2610.11873 arxiv.org/pdf/2610.11873 arxiv.org/html/2610.11873

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Varun Gumma, Navonil Majumdar, Soujanya Poria: SemField: A Simple, Linear, Continuous, yet Robust Semantic Watermark arxiv.org/abs/2610.11848 arxiv.org/pdf/2610.11848 arxiv.org/html/2610.11848

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Ines Ortega-Fernandez, Mateusz Kowalczyk, Keri Warr: Anytime-valid detection of LLM weight exfiltration arxiv.org/abs/2610.11843 arxiv.org/pdf/2610.11843 arxiv.org/html/2610.11843

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Andrei Neagu, Mara-Cristina Sterian, Paul Irofti: Host Attack Graph for Botnet Propagation arxiv.org/abs/2610.11640 arxiv.org/pdf/2610.11640 arxiv.org/html/2610.11640

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Luman Zhao, Minghui Xu, Yue Zhang, Yijun Yang: LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense arxiv.org/abs/2610.11634 arxiv.org/pdf/2610.11634 arxiv.org/html/2610.11634

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Li Lu, Yanjie Zhao, Hongjie Chen, Haoyu Wang: Where Do the Tokens Go? Understanding and Reducing Costs in LLM Agents for Vulnerability Discovery arxiv.org/abs/2610.11602 arxiv.org/pdf/2610.11602 arxiv.org/html/2610.11602

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Varun Kohli, Lee Bing Cheng, Nur Hazim Ghazali, Gao Yuze, Daryl Poon, Dinil Mon Divakaran: SoK: Are LLMs Reliable at Source Code Recovery? A Taxonomy and Empirical Evaluation arxiv.org/abs/2610.11556 arxiv.org/pdf/2610.11556 arxiv.org/html/2610.11556

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Alessandro Colombo, Margherita Cozzolino, Stephan Krenn, Thomas Lor\"unser: Certifying Hidden Paths: Scalable Topology Assurance for QKD Networks arxiv.org/abs/2610.11513 arxiv.org/pdf/2610.11513 arxiv.org/html/2610.11513

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Zehui Liao, Qiang Li, Binghui Wang: EIFL: Efficiently Protecting Global Model Privacy and Integrity Against an Untrusted Server in Federated Learning arxiv.org/abs/2610.11511 arxiv.org/pdf/2610.11511 arxiv.org/html/2610.11511

011

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Takahito Yoshizawa, Aysajan Abidin, Edoardo Pena-Gonzalez, Bart Preneel: A Zero-Knowledge Signature Framework for Efficient Post-Quantum Message Authentication in Cooperative Automated Driving arxiv.org/abs/2610.11490 arxiv.org/pdf/2610.11490 arxiv.org/html/2610.11490

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Liaoran Xu, Weizhi Liu, Zhaoxia Yin: MARC: Multi-Bit Watermarking for Autoregressive Audio Generation against Codec Attacks arxiv.org/abs/2610.11488 arxiv.org/pdf/2610.11488 arxiv.org/html/2610.11488

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Masaki Hashimoto, Ruo Ando, Toshiyuki Maeda, Hidehiko Tanaka: A Survey of Security Research for Operating Systems arxiv.org/abs/2610.11471 arxiv.org/pdf/2610.11471 arxiv.org/html/2610.11471

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Chiara Bonfanti, Cataldo Basile: GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity arxiv.org/abs/2610.11467 arxiv.org/pdf/2610.11467 arxiv.org/html/2610.11467

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Giulio Caldarelli: On-Chain Archaeology of Bitcoin Oracles: Evidence of Use under Limited Observability arxiv.org/abs/2610.11439 arxiv.org/pdf/2610.11439 arxiv.org/html/2610.11439

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Makeenkova, Olgun, Bostanc{\i}, Y\"uksel, Galanopoulos, Mutlu: MORDOR:Mitigating Overheads of Read Disturbance Preventive Operations via Elastic Refresh Scheduling arxiv.org/abs/2610.11398 arxiv.org/pdf/2610.11398 arxiv.org/html/2610.11398

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Jun Yao, Chao Wang, Yupeng Qiu, Zehua Ma, Weiming Zhang, Bin Liu, Han Fang: ProxyEraseAgent: Blind Watermark Removal in the Wild arxiv.org/abs/2610.11290 arxiv.org/pdf/2610.11290 arxiv.org/html/2610.11290

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Yingge Hu, Gautham Ramesh Babu, Mostafa Milani: Soft Voting for Policy-Aware Private Data Synthesis arxiv.org/abs/2610.11285 arxiv.org/pdf/2610.11285 arxiv.org/html/2610.11285

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Yiming Gao, Xuyuan Han, Honggang Hu: Provable Subexponential Algorithms for NIST Third-Round Lattice Families arxiv.org/abs/2610.11254 arxiv.org/pdf/2610.11254 arxiv.org/html/2610.11254

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Chang Qu, Zhaoyang Shi: BRACE: Differential Privacy for Dense Associative Memory with LSR Energy arxiv.org/abs/2610.11218 arxiv.org/pdf/2610.11218 arxiv.org/html/2610.11218

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Teruki Sano, Minoru Kuribayashi, Masao Sakai, Shuji Isobe, Eisuke Koizumi, Zhang Zhang, Satoru Matsumoto: Characterizing Statistical Separability in TP-CRIV for Probabilistic AI Models arxiv.org/abs/2610.11163 arxiv.org/pdf/2610.11163 arxiv.org/html/2610.11163

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Ye, Li, He, Xie, Zhang, Wang, Zeng, Chen, Wang, Wang, Zhou: False Claims, Credible Images: A Red-Teaming Benchmark for Commercial Image Generators arxiv.org/abs/2610.11112 arxiv.org/pdf/2610.11112 arxiv.org/html/2610.11112

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Jihoon Jang, Hyunju Park, Jebin Kim, Seokhie Hong, Suhri Kim: Accelerating HQC for Post-Quantum TLS 1.3 on x86 IoT Gateways arxiv.org/abs/2610.11107 arxiv.org/pdf/2610.11107 arxiv.org/html/2610.11107

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Min-Young Yu, Tony Kim, Jang Won Choi: NOMOS: Compiling Written Policies into Statically Verified Tool-Call Gates for LLM Agents arxiv.org/abs/2610.11030 arxiv.org/pdf/2610.11030 arxiv.org/html/2610.11030

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Dominik Blain: The Hint Weight of ML-DSA Signatures Is Key-Dependent: An Empirical Study across the Three FIPS 204 Parameter Sets arxiv.org/abs/2610.10992 arxiv.org/pdf/2610.10992 arxiv.org/html/2610.10992

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Adam Y. J. Jones, Yu Yuan, Sergio Maffeis: Speedbumps: Rejection Attacks on Speculative Decoding arxiv.org/abs/2610.10929 arxiv.org/pdf/2610.10929 arxiv.org/html/2610.10929

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Sahan Sanjaya, Prabhat Mishra: Power Side-Channel Membership Inference Attack on Embedded Machine Learning arxiv.org/abs/2610.10909 arxiv.org/pdf/2610.10909 arxiv.org/html/2610.10909

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Yuhan Ma, Jiongchi Yu, Xiaofei Xie, Qiang Hu, Zhiyi Zhang, Junjie Wang: When Flaws Cascade: Understanding Vulnerabilities and Exploitation Chains in JavaScript Engines arxiv.org/abs/2610.10844 arxiv.org/pdf/2610.10844 arxiv.org/html/2610.10844

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Muhammed Salih Kayhan, Qiben Yan: Detection-Guided Adaptive Purification with Diffusion Models for Robust Audio Deepfake Detection arxiv.org/abs/2610.10752 arxiv.org/pdf/2610.10752 arxiv.org/html/2610.10752

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Qiaolin Qin, Wanpeng Li, Benoit Baudry, Lorenzo De Carli, Heng Li, Ettore Merlo: DITTO: A Context-aware Pickle-based Pre-Trained Model Scanner for Effective Security Audits arxiv.org/abs/2610.10735 arxiv.org/pdf/2610.10735 arxiv.org/html/2610.10735

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Punit Suketu Patel: SoK: Failure Modes in Common Criteria Product Evaluation - A Taxonomy and Design-for-Evaluability Guidance arxiv.org/abs/2610.10644 arxiv.org/pdf/2610.10644 arxiv.org/html/2610.10644

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Yi Wang, Xiuyuan Qi, Dongqi Han, Dongsheng Li, Wenjie Wang: Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models arxiv.org/abs/2610.10625 arxiv.org/pdf/2610.10625 arxiv.org/html/2610.10625

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

William Guey, Rashik Jahangir, Pierrick Bougault, Vitor D. de Moura, Wei Zhang, Jos\'e O. Gomes: When AI Finds Hidden Messages, Does It Report? arxiv.org/abs/2610.10620 arxiv.org/pdf/2610.10620 arxiv.org/html/2610.10620

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Qilin Zhou, Zhengyuan Wei, Haipeng Wang, Zhuo Wang, Shuo Liu, W. K. Chan: MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Ma... arxiv.org/abs/2610.10617 arxiv.org/pdf/2610.10617 arxiv.org/html/2610.10617

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Jie Liao, Simeng Qin, Wenqi Ren, Wei Zhou, Junhao Wen, Ranjie Duan, Yang Liu, Xiaojun Jia: PyCache Trap: The Inspection-Execution Gap in Agent Skill Scanners arxiv.org/abs/2610.10612 arxiv.org/pdf/2610.10612 arxiv.org/html/2610.10612

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Saimon Amanuel Tsegai, Alex Kantchelian, Danfeng, Yao, Peng Gao: From Investigation Failures to Reliable SOC Agents: Understanding and Improving LLM-Based Alert Triage arxiv.org/abs/2610.10608 arxiv.org/pdf/2610.10608 arxiv.org/html/2610.10608

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

Hamed Khosravi, Xiaoming Huo: Certified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging arxiv.org/abs/2610.10597 arxiv.org/pdf/2610.10597 arxiv.org/html/2610.10597

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 21h

[2026-10-09 Fri (UTC), 49 new articles found for csCR Cryptography and Security]

000