Sabrina Sadiekh
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2ML×1AI×1NLP×1
Frequent co-authors
Research Timeline
2026
Towards Understanding the Robustness of Sparse Autoencoders
The paper demonstrates that integrating Sparse Autoencoders (SAEs) into transformer residual streams significantly enhances the robustness of Large Language Models against various jailbreak attacks by reshaping the optimization geometry.
GLiNER Guard: Unified Encoder Family for Production LLM Safety and Privacy
GLiNER Guard (GLiGuard) introduces a unified, efficient encoder family that simultaneously performs safety classification and PII detection in a single forward pass, offering a practical, low-cost alternative for always-on LLM moderation.
Highlighted terms show continued research focus across papers
Papers
cs.CRRecentMay 6, 2026
GLiNER Guard: Unified Encoder Family for Production LLM Safety and Privacy
GLiNER Guard (GLiGuard) introduces a unified, efficient encoder family that simultaneously performs safety classification and PII detection in a single forward pass, offering a practical, low-cost alt…
View →
cs.LGcs.AIcs.CLRecentApr 20, 2026