Jame Silberrad Brown Center for Artificial Intelligence

AI & ML interests

None defined yet.

Recent Activity

amanchadha  authored a paper 13 days ago

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations

amanchadha  authored a paper 13 days ago

AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)

amanchadha  authored a paper 27 days ago

Human-Readable Adversarial Prompts: An Investigation into LLM Vulnerabilities Using Situational Context

View all activity

Team members 7