AI safety researcher

Ponnurangam Kumaraguru

Google Scholar dblp OpenReview Homepage

Last 12 months10 papers

Interpretability 1

AI safety papers from the last year

On this site: 20 papers

October 2026

PrinGS: Privacy Preservation in Gaussian Splatting
Oct 26arXiv ↗

September 2026

Can Data Attribution Filter Out Subliminal Learning? Not Reliably
Sep 17arXiv ↗

August 2026

MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning
Aug 13arXiv ↗

July 2026

OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization
Jul 22arXiv ↗

May 2026

Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
May 11InterpretabilityarXiv ↗

April 2026

ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues
Apr 2arXiv ↗

March 2026

January 2026

Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMs
Jan 7arXiv ↗

December 2025

PrivacyBench: A Conversational Benchmark for Evaluating Privacy in Personalized AI
Dec 31arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.