Nina Dubicka

GenerativeAI Academic Research Team (GART), Capgemini Insights & Data, Wrocław, Poland

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)Eval Frameworks & Benchmarks (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Paweł Majewski (1)Kacper Marczak (1)Jedrzej Podolak (1)Bartosz Sochaj (1)

Papers (1)

May 5, 2026

Wrocław University of Science and Technology2w ago·also GenerativeAI Academic Research Team (GART), Silesian University of Technology

Comprehensive Analysis of LLM Guardrails Approaches Preventing Harmful Content and Jailbreak Attacks

AWS Guardrails and NeMo stand out, achieving 96.8% and 93.9% accuracy respectively, proving that effective defenses against jailbreaks are within reach for commercial LLM deployments.

Paweł Majewski, Kacper Marczak, Nina Dubicka +4

Constitutional AI & AI Ethics Eval Frameworks & Benchmarks Red-Teaming & Adversarial Robustness

Search

Nina Dubicka

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)