I lead research on AI security and trustworthy machine learning, with a focus on adversarial attacks and defenses, robustness under deployment constraints, and secure perception systems. My work bridges theory, system-level design, and real-world evaluation, targeting vision, autonomous, embedded, and multimodal AI systems.

🔥 News

• 2026.01: 🎉 2 papers accepted at ICLR 2026
• 2025.11: 🎉 1 paper accepted at DATE 2026
• 2025.10: 🎉 Selected as Top Reviewer at NeurIPS 2025
• 2025.06: 🎉 1 paper accepted at ICCV 2025
• 2024.06: 🎉 1 paper accepted at IROS 2024
• 2024.06: 🎉 3 papers accepted at ICIP 2024
• 2024.02: 🎉 1 paper accepted at CVPR 2024
• 2024.02: 🎉 1 paper accepted at DAC 2024

Research Overview

My research aims to advance the security, robustness, and trustworthiness of machine learning systems under adversarial threats and realistic deployment constraints. I study how architecture choices (e.g., Vision Transformers), quantization and approximation, physical-world effects, and multimodal interactions shape both vulnerabilities and defenses. A recurring theme in my work is breaking brittle alignment—semantic, gradient, or representational—to improve robustness while preserving efficiency and deployability.

Selected Research Projects

Below are representative research projects spanning adversarial machine learning, robustness, and secure AI systems.

ICLR 2026: DRIFT: Divergent Response in Filtered Transformations

DRIFT is a stochastic ensemble defense that disrupts gradient consensus across transformations, significantly reducing adversarial transferability while preserving clean accuracy.

Project | Paper

ICLR 2026: TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks

Disrupts semantic and gradient alignment across quantized models to prevent patch transferability.

Project | Paper

NeurIPS 2026: TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers

TESSER introduces spectral and semantic regularization to enhance adversarial transferability from Vision Transformers to CNNs and hybrid architectures, achieving state-of-the-art black-box attack performance across diverse model families.

Project | Paper

CVPR 2024: DAP: Dynamic Adversarial Patch

DAP proposes an adaptive adversarial patch that dynamically adjusts spatial placement and appearance to evade person detectors under real-world transformations.

Project | Paper

🏆 Awards & Honors

• Outstanding Reviewer, NeurIPS 2025
• Best Senior Researcher Award, eBRAIN Lab, NYU Abu Dhabi (2023)
• Erasmus+ Scholarship (2019)
• DAAD Scholarships: ATIoT (2018), Young ESEM Program (2016)

🧑‍🏫 Academic Service & Community

• Reviewer: ICLR, NeurIPS, ICCV, CVPR, AAAI, ECCV, DAC, DATE, ICIP; IEEE TIFS, TCAD, TCSVT
• Tutorial Organizer & Speaker: ML Security in Autonomous Systems, IROS 2024

📬 Contact & Links

• Email: ag9321@nyu.edu

I am always open to collaborations on AI security, adversarial robustness, and trustworthy ML systems.