Amira Guesmi

Amira Guesmi

she/her

Research Team Leader @ NYU Abu Dhabi — AI Security, Adversarial ML, Robust Vision, Edge/Quantized Models

About

Dr. Amira Guesmi

Research Team Leader, Electrical and Computer Engineering
New York University Abu Dhabi

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.

📚 Recent Publications by Research Theme

1. Robustness and Security of Quantized & Approximate Neural Networks

  • TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks (ICLR 2026)
  • Defending with Errors: Approximate Computing for Robustness of Deep Neural Networks (CoRR 2022)
  • Defensive Approximation: Securing CNNs Using Approximate Computing (ASPLOS 2021)

2. Adversarial Machine Learning — Foundations

  • DRIFT: Divergent Response in Filtered Transformations for Robust Adversarial Defense (ICLR 2026)
  • TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers via Spectral and Semantic Regularization (CoRR 2025)
  • Anomaly Unveiled: Securing Image Classification Against Adversarial Patch Attacks (ICIP 2024)
  • Defending Against Adversarial Patches Using Dimensionality Reduction (DAC 2024)
  • ROOM: Adversarial Machine Learning Attacks under Real-Time Constraints (IJCNN 2022)
  • SIT: Stochastic Input Transformation to Defend Against Adversarial Attacks (IEEE Design & Test 2021)

3. Adversarial Machine Learning — Vision & Autonomous Systems

  • DAP: A Dynamic Adversarial Patch for Evading Person Detectors (CVPR 2024)
  • SSAP: Shape-Sensitive Adversarial Patch for Monocular Depth Estimation (IROS 2024)
  • SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation (IEEE Access 2024)
  • AdvART: Adversarial Art for Camouflaged Object Detection Attacks (ICIP 2024)
  • PatchBlock: A Lightweight Defense Against Adversarial Patches for Embedded EdgeAI Devices (DATE 2026)
  • AdvRain: Adversarial raindrops to attack camera-based smart vision systems (Information 2023)
  • Adversarial attack on radar-based environment perception systems (CoRR 2022)

4. Physical-World and Multi-Modal Adversarial Threats: Surveys

  • Navigating threats: A survey of physical adversarial attacks on lidar perception systems in autonomous vehicles (CoRR 2024)
  • Physical adversarial attacks for camera-based smart systems: Current trends, categorization, applications, research challenges, and future outlook (IEEE Access 2023)

5. Privacy-Preserving and Trustworthy Machine Learning

  • Exploring machine learning privacy/utility trade-off from a hyperparameters lens (IJCNN 2023)

6. Interpretability and Robustness

  • Exploring the Interplay of Interpretability and Robustness in Deep Neural Networks: A Saliency-Guided Approach (ICIP 2024)

7. Continual Learning and Representation Dynamics

  • Examining Changes in Internal Representations of Continual Learning Models Through Tensor Decomposition, (Unconference 2024)

8. Vision–Language Model (VLM) Security, Hallucination, and Privacy

  • Do Not Leave a Gap (under review)

(See the Publications page for full lists and links.)

🏆 Awards & Honors

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

🧑‍🏫 Academic Service & Community

  • Reviewer: ICLR, NeurIPS, ICCV, CVPR, 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.