Beyond the Patch: Reconstructing an Incomplete-Fix Patch Bypass in LLM Agent Frameworks with Control-Gated, Benign Probes
Chaitanya Garware
https://t.co/av7w0pYPft [𝚌𝚜.𝙲𝚁]
Replay-Augmented Regularisation for Class-Incremental Network Intrusion Detection: A Three-Dataset Evaluation of EWC and LwF
Mohammed Fackruddin Tusher, Muhammad Iqbal Hossain
https://t.co/S1Bii1Ptpe [𝚌𝚜.𝙲𝚁]
Designing Deceptive Model Organisms that Successfully Evade Auditing
Vasisht Duddu, Mark Wang, Lipeng He, Tim G. J. Rudner
https://t.co/Sgog49kwul [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙰𝙸]
Where the Evidence Lives: Measuring Privacy and Diagnosability of Exported AI-Agent Traces
Chang Xu, Hao Wang, Gedi Zhou, Junyuan Tan
https://t.co/ijEhJfKEuz [𝚌𝚜.𝙲𝚁]
💬Accepted to S2AI 2026, co-located with IEEE BigData 2026
Understanding Users' Security, Privacy, and Trust Concerns in Healthcare AI Systems
Tushar Nayan, Mohammed Al Duniawi, Song Fang, Aokun Chen, Arjun Arunasalam, Ruimin Sun
https://t.co/NM4WTcDeqM [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙲𝚈]
Security of Deep Research Agents: Attack Surface, Defenses, Benchmarks, and Agenda Seeding against Research Planning
Yang Luo, Guangpu Chen, Yichen Liu, Zhaoyu Chen, Yifeng Gao, Zhiyang Ding, Qingni Shen, Zhonghai Wu
https://t.co/5EN1CYjaPW [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙰𝙸]
CHERI under Fault Injection: An Emulation-Based Security Evaluation of Capability Hardware Enhanced RISC Instructions
Eva Sophia Schreyer
https://t.co/ri3OBDpWdM [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙰𝚁]
💬Submitted to KTH Royal Institute on Technology as a Master Thesis
Local Order Matters: A Lightweight CPU-Trainable CNN for Website Fingerprinting on Defended Tor Traffic
https://t.co/IUdLrz3c5o [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]
💬Submitted to the 11th International Conference on Computer and Information Processing Technology (ISCIPT 2026)
Protecting the System, Stranding the User: The Limits of Multi-Agent Authorization
Gurpriya Bhatia, Clifford Neuman
https://t.co/oXJSU5zku7 [𝚌𝚜.𝙲𝚁 𝚌𝚜.𝙼𝙰]