Lattice AI Research

Research focus

Constitutional AI & AI Ethics (2)RLHF & Preference Learning (1)Data Curation & Synthetic Data (1)

Frequent co-authors

Jannatul Ferdous (2)Md. Zahidul Islam (1)Jannatul Ferdous (1)Rafiqul Islam (1)

Papers (2)

Jul 8, 2026

Jannatul Ferdous +25d ago

SA-DRL: Security-Aware Deep Reinforcement Learning for Ransomware Detection with Asymmetric Reward Design

Asymmetric reward design in deep reinforcement learning can drastically reduce false negatives in ransomware detection, achieving a remarkable 67.6% improvement over traditional methods.

Jannatul Ferdous, Rafiqul Islam, Md. Zahidul Islam

Constitutional AI & AI Ethics RLHF & Preference Learning

Jul 7, 2026

Jannatul Ferdous +46d ago

Auditable Machine Unlearning for Privacy-Compliant Ransomware Detection Using Multi-Shard SISA and Deep Reinforcement Learning

Achieving near-perfect ransomware detection while ensuring compliance with privacy regulations through efficient and auditable unlearning methods.

Jannatul Ferdous, Jannatul Ferdous, Rafiqul Islam +2

Constitutional AI & AI Ethics Data Curation & Synthetic Data

Search

Rafiqul Islam

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)