Giulio Zizzo

Title

Staff Research Scientist

Bio

Giulio's research interests focus on the security and robustness of machine learning. Recently, he has been working on adversarial machine learning with a focus verifiable methods and the security of Federated Learning.

He obtained his PhD from Imperial College London in 2021 which focuses on adversarial and robust machine learning. He joined IBM Research in 2021 and has continued his research in private and robust ML and contributing to open source projects such as ART (Adversarial Robustness Toolbox) and various Horizon Europe programmes.

Publications

Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
- - Ambrish Rawat
  - Stefan Schoepf
  - et al.
- 2024
- NeurIPS 2024
MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks
- - Giandomenico Cornacchia
  - Kieran Fraser
  - et al.
- 2024
- AIES 2024
Adversarial Robustness of Deep Learning-based Malware Detectors via (De)Randomized Smoothing
- - Daniel Gibert
  - Giulio Zizzo
  - et al.
- 2024
- IEEE Access
Domain Adaptation for Time series Transformers using One-step fine-tuning
- - Subina Khanal
  - Seshu Tirupathi
  - et al.
- 2024
- AAAI 2024
Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resilience
- - Janvi Thakkar
  - Giulio Zizzo
  - et al.
- 2024
- AAAI 2024
Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation
- - Janvi Thakkar
  - Giulio Zizzo
  - et al.
- 2024
- AAAI 2024
Certified Robustness of Static Deep Learning-based Malware Detectors against Patch and Append Attacks
- - Daniel Gibert
  - Giulio Zizzo
  - et al.
- 2023
- CCS 2023
Towards a Practical Defense Against Adversarial Attacks on Deep Learning-Based Malware Detectors via Randomized Smoothing
- - Daniel Gibert
  - Giulio Zizzo
  - et al.
- 2023
- ESORICS 2023
Machine Learning Platform for Extreme Scale Computing on Compressed IoT Data
- - Seshu Tirupathi
  - Dhaval Salwala
  - et al.
- 2022
- Big Data 2022
Federated Continual Learning with Differentially Private Data Sharing
- - Giulio Zizzo
  - Ambrish Rawat
  - et al.
- 2022
- NeurIPS 2022

Visit Google Scholar

Projects

Adversarial Robustness Toolbox

Securing AI models with the Adversarial Robustness Toolbox

Adversarial Robustness and Privacy

Federated Systems

Incremental Machine Learning for Extreme Scale Computing

AutoML for incremental machine learning algorithms for big time-series data.

View more projects

Top collaborators

Giulio Zizzo

Title

Bio

Publications

Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI

MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks

Adversarial Robustness of Deep Learning-based Malware Detectors via (De)Randomized Smoothing

Domain Adaptation for Time series Transformers using One-step fine-tuning

Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resilience

Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation

Certified Robustness of Static Deep Learning-based Malware Detectors against Patch and Append Attacks

Towards a Practical Defense Against Adversarial Attacks on Deep Learning-Based Malware Detectors via Randomized Smoothing

Machine Learning Platform for Extreme Scale Computing on Compressed IoT Data

Federated Continual Learning with Differentially Private Data Sharing

Projects

Adversarial Robustness Toolbox

Federated Systems

Incremental Machine Learning for Extreme Scale Computing

Top collaborators

Ambrish Rawat

Mark Purcell

Seshu Tirupathi

Muhammad Zaid Hameed