WalledAI evolved as an offshoot of Rishab Bharadwaj’s PhD research at the Singapore University of Technology and Design (SUTD). Under the guidance of Prof. Soujanya Poria (PhD), Rishab set out to explore critical issues in AI safety and fairness. Their groundbreaking work, particularly in investigating gender bias in BERT models, exposed significant vulnerabilities in AI systems. They also uncovered a wide range of other safety and data privacy flaws in leading state-of-the-art large language models (LLMs) and AI systems.These findings highlighted serious security implications that hindered large-scale AI adoption. Determined to bridge the gap between academic research and real-world applications, Rishab and Prof. Soujanya set out to build safeguards that would allow AI to be adopted safely—without legal, ethical, or security complications.After months of intensive research and multiple breakthroughs, WalledAI was formally founded.Today, we stand as pioneers in AI security, ensuring that as AI continues to evolve, it remains transparent, safe, and aligned with human values.
Quick Links#
Modified at 2025-09-05 09:54:52
