iiinova — where your digital self keeps evolving

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Zhen Liang, Hai Huang, Wentao Chen: CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion arxiv.org/abs/2609.39902 arxiv.org/pdf/2609.39902 arxiv.org/html/2609.39902

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Rajneesh Anand, Neeraj Lakshmanan, Masoud Yari: PassGPT+: Leveraging Linguistic Priors for Password Modeling arxiv.org/abs/2609.39880 arxiv.org/pdf/2609.39880 arxiv.org/html/2609.39880

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Kotevska, Jha, Bellet, Hu, Bastian, da Silva, Madduri, Kim: Privacy Foundations for Multi-Institutional Scientific Artificial Intelligence arxiv.org/abs/2609.39787 arxiv.org/pdf/2609.39787 arxiv.org/html/2609.39787

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Hans Schmiedel, Jiangshan Yu: Path-Finding, Orbit State Preparation, and the Security of Invariant Quantum Money arxiv.org/abs/2609.39774 arxiv.org/pdf/2609.39774 arxiv.org/html/2609.39774

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Jieke Shi, Yuchen Chen, Junda He, Yue Liu, David Lo: Aletheia: Permission-Minimality Testing for Coding-Agent Rules arxiv.org/abs/2609.39678 arxiv.org/pdf/2609.39678 arxiv.org/html/2609.39678

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Tobias Kaisar, Aritra Dhar: Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents arxiv.org/abs/2609.39607 arxiv.org/pdf/2609.39607 arxiv.org/html/2609.39607

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Zawad Yalmie Sazid, Robert Abbas: Cybersecurity in Edge Computing: A Trust-Aware Federated Hybrid Intrusion Detection Framework arxiv.org/abs/2609.39584 arxiv.org/pdf/2609.39584 arxiv.org/html/2609.39584

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Zezhong Wang, Xueyang Tang, Rui Lian, Yang Lou, Heqing Huang: Speculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent Attacks arxiv.org/abs/2609.39549 arxiv.org/pdf/2609.39549 arxiv.org/html/2609.39549

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Jihun Han, Yejin Jang, Byung Il Kwak, Mee Lan Han: ActionGuard: Tool Call Authorization under Poisoned Skills arxiv.org/abs/2609.39450 arxiv.org/pdf/2609.39450 arxiv.org/html/2609.39450

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Soohan Lim, Hyundong Jin, Yo-Sub Han: SEW: Style-Encoded Watermarking of LLM-Generated Code arxiv.org/abs/2609.39414 arxiv.org/pdf/2609.39414 arxiv.org/html/2609.39414

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Emna Bouguerra, Ibtissam Harrouche, Ferran Alborch, Melek \"Onen: Link Inference Attack on Privacy-Preserving Knowledge Graphs arxiv.org/abs/2609.39362 arxiv.org/pdf/2609.39362 arxiv.org/html/2609.39362

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Wenxin Wu, Lingyong Yan, Lei Sha, Shuaiqiang Wang, Jiashu Zhao: Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents arxiv.org/abs/2609.39352 arxiv.org/pdf/2609.39352 arxiv.org/html/2609.39352

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Atul Khekade, Ritesh Kakkad, Wanwiset Peerapatanapokin, Behnam Mohammadkhani: XIM: The XDC Interledger Messaging Protocol arxiv.org/abs/2609.39310 arxiv.org/pdf/2609.39310 arxiv.org/html/2609.39310

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Jiaqing Li, Shide Zhou, Zhibo Zhang, Yuxi Li, Tianlong Yu, Kailong Wang: Faithful Dual-constrained Erasure for Robust LLM Safety Alignment arxiv.org/abs/2609.39279 arxiv.org/pdf/2609.39279 arxiv.org/html/2609.39279

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Maksym Petkus: MultiTable: A Faster Hash Table at any Physical Load Factor up to and Including One arxiv.org/abs/2609.39233 arxiv.org/pdf/2609.39233 arxiv.org/html/2609.39233

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Xinwei Zhang, Aoting Hu, Hangcheng Liu, Shuchao Pang, Qingqing Ye, Haibo Hu: SteerProbe: Learning to Bypass Safety Steering in Vision-Language Models arxiv.org/abs/2609.39117 arxiv.org/pdf/2609.39117 arxiv.org/html/2609.39117

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Zeming Liu, Qibai Chen, Jingtao Zhang, Hang Lyu: RAGScope: A Leakage-Controlled, Cost-Aware Evidence-Gating Protocol for RAG Hallucination Triage arxiv.org/abs/2609.39075 arxiv.org/pdf/2609.39075 arxiv.org/html/2609.39075

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Yan Wang, Zhihao Zhang, Ke Chen, Kai Chen, Yaqin Zhang, Duohe Ma, Jun Dai, Xiaoyan Sun: Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents arxiv.org/abs/2609.39065 arxiv.org/pdf/2609.39065 arxiv.org/html/2609.39065

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Deema Alnuhait, Gengyu Wang, Muhammad Khalifa, Hao Peng: Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems arxiv.org/abs/2609.39050 arxiv.org/pdf/2609.39050 arxiv.org/html/2609.39050

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Yang Wang: Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses arxiv.org/abs/2609.38983 arxiv.org/pdf/2609.38983 arxiv.org/html/2609.38983

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Leo Y. Lin, Mikhail Kuznetsov, Muslum Ozgur Ozmen, Z. Berkay Celik: Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners arxiv.org/abs/2609.38971 arxiv.org/pdf/2609.38971 arxiv.org/html/2609.38971

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Yu Wang, Shuhao Li, Tao Yin, Ziyang Li, Xueying Zhao, Peishuai Sun, Jiang Xie: APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry arxiv.org/abs/2609.38954 arxiv.org/pdf/2609.38954 arxiv.org/html/2609.38954

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Tsubasa Takahashi, Takumi Hiraoka: PrivCert: Certifying Statement Support under Differential Privacy arxiv.org/abs/2609.38934 arxiv.org/pdf/2609.38934 arxiv.org/html/2609.38934

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Wenyu Chen, Li Wang, Chuanchao Zang, Xiangtao Meng, Xinyu Gao, Jianing Wang, Zheng Li, Shanqing Guo: SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs arxiv.org/abs/2609.38899 arxiv.org/pdf/2609.38899 arxiv.org/html/2609.38899

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Hongyuan Li, Ke Wang, Wei Zhou, Le Guan: SoK: A Large-Scale Empirical Study of Emulation-Based Dynamic Analysis Research for ARM Cortex-M Firmware (Extended Version) arxiv.org/abs/2609.38872 arxiv.org/pdf/2609.38872 arxiv.org/html/2609.38872

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Zewei Deng, Muhammad Siddeek, Liyan Xie, Mohamed Seif, Mengdi Wang, H. Vincent Poor, Andrea Goldsmith: Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes arxiv.org/abs/2609.38722 arxiv.org/pdf/2609.38722 arxiv.org/html/2609.38722

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Andrea Rondelli: Z-Sigil: A Public-Key Cryptosystem with Chained Selection over a Fiber Bundle of Module-Lattice Keys arxiv.org/abs/2609.38668 arxiv.org/pdf/2609.38668 arxiv.org/html/2609.38668

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Danqing Wang, Baolin Peng, Zhepei Wei, Isadora White, Wenlin Yao, Hao Cheng, Qianhui Wu, Minseon Kim, Xingdi Yuan, Lei Li, Jianfeng Gao: SecureVibe: Making Vibe Coding More Secure arxiv.org/abs/2609.38606 arxiv.org/pdf/2609.38606 arxiv.org/html/2609.38606

010

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Syed Ghazanfar Abbas, Gang Wang, Dongyan Xu: RISK: Auditing Industrial Control Systems for Too-Late-to-Recover Vulnerabilities arxiv.org/abs/2609.38528 arxiv.org/pdf/2609.38528 arxiv.org/html/2609.38528

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Qiuyu Ren, Sudipta Paria, Aritra Dasgupta, Swarup Bhunia: Security-Enhanced Seed-Based Weight Quantization for Large Language Models arxiv.org/abs/2609.38477 arxiv.org/pdf/2609.38477 arxiv.org/html/2609.38477

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Alexandra Souly, Kai Fronsdal, Abby D'Cruz, Xander Davies, Robert Kirk: Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks arxiv.org/abs/2609.38415 arxiv.org/pdf/2609.38415 arxiv.org/html/2609.38415

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Prakriti Baral, Zhuoyun Qian, Hailu Xu, Fangtian Zhong: Behavior-Centric Malware Classification with Fine-Grained Malicious Logic Localization arxiv.org/abs/2609.38390 arxiv.org/pdf/2609.38390 arxiv.org/html/2609.38390

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Yelyzaveta (Lisa), Husieva, Lauren Alvarez: The Geometry of Harmfulness in Multi-Turn Attacks arxiv.org/abs/2609.38389 arxiv.org/pdf/2609.38389 arxiv.org/html/2609.38389

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Ziyan An, John Stankovic, Meiyi Ma: LogiC-Diff: Embedding Security Properties Into AI-Enabled Cyber-Physical Systems arxiv.org/abs/2609.38381 arxiv.org/pdf/2609.38381 arxiv.org/html/2609.38381

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Chaoyu Zhang, Shanghao Shi, Heng Jin, Ning Wang, Y. Thomas Hou, Wenjing Lou: Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning arxiv.org/abs/2609.38339 arxiv.org/pdf/2609.38339 arxiv.org/html/2609.38339

011

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Zhuo Liu, Moxin Li, Zhixin Ma, Wentao Shi, Wenjie Wang, Fuli Feng: HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control arxiv.org/abs/2609.38291 arxiv.org/pdf/2609.38291 arxiv.org/html/2609.38291

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Guillaume Salha-Galvan, Jiaying Xu: Privacy in Personalized AI Is a System Property, Not Just a Model Property arxiv.org/abs/2609.38289 arxiv.org/pdf/2609.38289 arxiv.org/html/2609.38289

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Nafisa Anjum, M. Rasel Mahmud: Beyond the Headset: A Systematization of Knowledge on Extended Reality Privacy and Security in Healthcare arxiv.org/abs/2609.38281 arxiv.org/pdf/2609.38281 arxiv.org/html/2609.38281

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Yurong Hao, Wen Zhou, Guowei Guan, Tiantong Wu, Fuyao Zhang, Wei Yang Bryan Lim: VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents arxiv.org/abs/2609.38270 arxiv.org/pdf/2609.38270 arxiv.org/html/2609.38270

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Mustafa Arslan: Janus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMs arxiv.org/abs/2609.38266 arxiv.org/pdf/2609.38266 arxiv.org/html/2609.38266

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Mehran Moradi, Reza Zamani, Phil Aupke, Andreas Theocharis, Andreas Kassler: Robustness of Local Energy Markets to Cyberattacks: Case Study of False Data Injection arxiv.org/abs/2609.38258 arxiv.org/pdf/2609.38258 arxiv.org/html/2609.38258

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Mou, Lu, Ni, Hong, Shen, Li, Zhang, Zhou, Ren: CollageAttack: Exploiting Cross-Modal Alignment Flaws in T2I Models through Spatial Text Composition arxiv.org/abs/2609.38253 arxiv.org/pdf/2609.38253 arxiv.org/html/2609.38253

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Titouan Millet, Thomas Valade, Fran\c{c}ois Gonnet, Mounira Msahli: Multilayer Forensic Tampering Detection arxiv.org/abs/2609.38252 arxiv.org/pdf/2609.38252 arxiv.org/html/2609.38252

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Chenqi Kong, Song Xia, Anwei Luo, Peisong He, Alex C. Kot, Yuming Fang: Forensic-Aware Continual Adaptation for Image Forgery Localization arxiv.org/abs/2609.38251 arxiv.org/pdf/2609.38251 arxiv.org/html/2609.38251

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Soeun Han, Jisoo Lee, Jeongyong Shim, Eunkyeong Lee, Eunmi Kim: SURE: Framework for Safety to Construct Trustworthy AI arxiv.org/abs/2609.38249 arxiv.org/pdf/2609.38249 arxiv.org/html/2609.38249

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Dongxu Cui, Zhichao Gu, Ping Zheng, Wenshuai Xi, Simeng Han, Yong Liao: ContractWarden: Kernel-Enforced Damage Boundaries for AI Agents via Human-Authorized Contracts arxiv.org/abs/2609.38248 arxiv.org/pdf/2609.38248 arxiv.org/html/2609.38248

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Oguzhan Baser, Kaan Kale, Sriram Vishwanath, Sandeep Chinchali: ModalFidelity: Routing Modalities for Deepfake Detection on a Budget arxiv.org/abs/2609.38246 arxiv.org/pdf/2609.38246 arxiv.org/html/2609.38246

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Dongxu Cui, Zhichao Gu, Ping Zheng, Simeng Han, Yong Liao: Agent-Warden: eBPF-Based Kernel-Native Process-File Provenance Tracking for LLM Agents arxiv.org/abs/2609.38245 arxiv.org/pdf/2609.38245 arxiv.org/html/2609.38245

000

arXiv cs.CR Cryptography and Security @cscr-bot.bsky.social · 15h

Keifer Lee: Inference-Layer Security: Defending Against Adversarial Inference and Infrastructure Abuse arxiv.org/abs/2609.38239 arxiv.org/pdf/2609.38239 arxiv.org/html/2609.38239

000