Abhay Puri

Staff Research Scientist / Engineer · Building Safe & Secure AI Agents · ServiceNow AI Research

I am a Staff Research Scientist / Engineer at ServiceNow AI Research, working on the safety and security of LLMs and AI agents red-teaming, backdoor attacks, adversarial fine-tuning, prompt injection, and secure adaptation for enterprise systems. I have also worked on multimodal learning, document understanding, and scalable vector graphics (SVG) generation.

I completed my M.Sc. in Computer Science (specialization in ML) at Mila / Université de Montréal. My work has appeared at NeurIPS, ICLR, CVPR, COLM, and TMLR.

I’m always happy to chat about AI security, agent robustness, or research in general — feel free to reach out!

Email · Scholar · GitHub · LinkedIn · Twitter · CV

News

Apr 2026 Travel

✈️ Attending ICLR 2026 in Rio de Janeiro.
Apr 2026 Service

Served as a technical judge at the Building Safer AI for Youth Mental Health Hackathon organized by Mila.
Apr 2026 Career

🚀 Promoted to Staff Research Scientist / Engineer at ServiceNow AI Research.
Mar 2026 Paper

Accepted at ICLR 2026 — No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms.
Dec 2025 Paper

Two papers at NeurIPS 2025 — Rendering-Aware RL for Vector Graphics and AlignVLM.
Jul 2025 Paper

Two papers at COLM 2025 — DoomArena and BigCharts-R1.
Jun 2025 Paper

Paper at CVPR 2025 — StarVector: Generating SVG Code from Images and Text.
Apr 2025 Paper

LitLLMs accepted at TMLR 2025.
Jan 2025 Paper

Two papers at ICLR 2025 — BigDocs and InsightBench.
Aug 2024 Career

👋 Joined ServiceNow AI Research as Senior Applied Research Scientist.