AI safety researcher

Amitava Das

Wipro AI Lab

Google Scholar dblp OpenReview ORCID

Last 12 months14 papers

AI safety papers from the last year

On this site: 26 papers

September 2026

Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time
Sep 3arXiv ↗

August 2026

GuardPaint:SpeculativeSafetyDecodingforText-to-ImageGeneration
Aug 22arXiv ↗

May 2026

MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
May 31arXiv ↗
MAAT: Multi-phase Adapter-Aware Targeted Unlearning
May 28arXiv ↗
Findings of the Counter Turing Test: AI-Generated Image Detection
May 20arXiv ↗
Findings of the Counter Turing Test: AI-Generated Text Detection
May 20arXiv ↗

April 2026

January 2026

December 2025

November 2025

Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria
Nov 22arXiv ↗

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