Get started
Author

Sabrina Sadiekh

Observed names: Sabrina A. Sadiekh, Sadiekh, Sabrina
ORCID: 0009-0008-4100-512X
Observed ORCID: 0009-0008-4100-512X
OpenAlex ID: A5125739421
Polarity-Aware Probing for Quantifying Latent Alignment in Language Models
2026 · Sabrina Sadiekh, Elena Ericheva, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 1
PDF
DUMA-Bench: A Dual-Control Multi-Agent Benchmark for Evaluating LLM Agent Security
2026 · Aleksandrov, Ivan, Kochnev, German, et al. · arXiv (Cornell University)
PDF
HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation
2026 · Oblakov, Nikita, Sadiekh, Sabrina, et al. · arXiv (Cornell University)
PDF
GLiNER Guard: Unified Encoder Family for Production LLM Safety and Privacy
2026 · Minko, Bogdan, Sadiekh, Sabrina, et al. · arXiv (Cornell University)
PDF
Cross-Lingual Jailbreak Detection via Semantic Codebooks
2026 · Alanova, Shirin, Minko, Bogdan, et al. · arXiv (Cornell University)
PDF
Towards Understanding the Robustness of Sparse Autoencoders
2026 · Saiyed, Ahson, Sadiekh, Sabrina, et al. · arXiv (Cornell University)
PDF
1062 - Polarity-Aware Probing for Quantifying Latent Alignment in Language Models
2026 · Association for Artificial Intelligence 2026, Agarwal, Chirag, et al. · Underline Science Inc.
Polarity-Aware Probing for Quantifying Latent Alignment in Language Models
2026 · Association for Artificial Intelligence 2026, Agarwal, Chirag, et al. · Underline Science Inc.
Towards Understanding the Robustness of Sparse Autoencoders
2026 · Ahson Saiyed, Sabrina Sadiekh, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
Analysis of locality and stability of extracted features in tasks defined by machine learning models
2025 · Sabrina A. Sadiekh, Aleksandr A. Rogov · Vestnik of Saint Petersburg University Applied Mathematics Computer Science Control Processes
PDF
Works count: 10
Citation count: 1
H-index: 1
I10-index:
Year
Topic
Type