-
Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation
Paper • 2611.06498 • Published -
Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5
Paper • 2610.33732 • Published • 3 -
The Price of Peeking: Anytime-Valid Leakage Detection on ML-KEM EM Traces
Paper • 2609.33597 • Published
AI & ML interests
AI security, trustworthy and offline generative AI, edge AI, retrieval-augmented generation, post-quantum cryptography, privacy-preserving machine learning
Recent Activity
Papers
Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation
Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5
securagen.ai
securagen.ai P.C. is an Athens-based company working on AI security, trustworthy and offline generative AI, and post-quantum cryptography.
We publish our research together with code and data, so that results can be inspected and reproduced.
Research
Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation arXiv:2611.06498 · Code & data · DOI
Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5 arXiv:2610.33732 · Code & data · DOI
The Price of Peeking: Anytime-Valid Leakage Detection on ML-KEM EM Traces arXiv:2609.33597 · Code · DOI
Links
- Website: securagen.ai
- GitHub: github.com/securagenai
-
Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation
Paper • 2611.06498 • Published -
Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5
Paper • 2610.33732 • Published • 3 -
The Price of Peeking: Anytime-Valid Leakage Detection on ML-KEM EM Traces
Paper • 2609.33597 • Published