Adversarial Robustness on Cognaptus

Adversarial Robustness on Cognaptus https://cognaptus.com/tags/adversarial-robustness/ Recent content in Adversarial Robustness on Cognaptus Hugo -- 0.145.0 en-us Tue, 17 Feb 2026 00:00:00 +0000 Reasoning Under Pressure: When Smart Models Second-Guess Themselves https://cognaptus.com/blog/2026-02-17-reasoning-under-pressure-when-smart-models-secondguess-themselves/ Tue, 17 Feb 2026 00:00:00 +0000 https://cognaptus.com/blog/2026-02-17-reasoning-under-pressure-when-smart-models-secondguess-themselves/ A close reading of why reasoning models are more resistant to multi-turn pressure, why they still flip, and why confidence-based defenses may fail when models become too confident in their own reasoning. SAFE Enough to Think: Federated Learning Comes for Your Brain https://cognaptus.com/blog/2026-01-14-safe-enough-to-think-federated-learning-comes-for-your-brain/ Wed, 14 Jan 2026 00:00:00 +0000 https://cognaptus.com/blog/2026-01-14-safe-enough-to-think-federated-learning-comes-for-your-brain/ A mechanism-first reading of SAFE, a federated EEG-BCI framework that tries to make privacy, robustness, and calibration-free decoding work together instead of politely sabotaging one another.