Mark Purcell

Title

Research Manager - Security Research, AI Security & PETs

Mark Purcell

Bio

Mark manages the AI Security & Privacy team in the Dublin Research Lab. The research topics for the team are the Security of Generative AI (guardrails, red-teaming) and Privacy Enhancing Technologies (PII detection, risk assessment, Differential Privacy).

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
Towards Assurance of LLM Adversarial Robustness using Ontology-Driven Argumentation
- - Tomas Bueno Momcilovic
  - Beat Buesser
  - et al.
- 2024
- xAI 2024
Pruning Federated Learning Models for Anomaly Detection in Resource-Constrained Environments
- - Simone Magnani
  - Stefano Braghin
  - et al.
- 2023
- Big Data 2023
Adaptive Aggregation For Federated Learning
- - K. R. Kallapalayam Radhakrishnan
  - Vinod Muthusamy
  - et al.
- 2022
- Big Data 2022
Machine Learning Platform for Extreme Scale Computing on Compressed IoT Data
- - Seshu Tirupathi
  - Dhaval Salwala
  - et al.
- 2022
- Big Data 2022
GOFLEX: Extracting, Aggregating and Trading Flexibility based on FlexOffers for 500+ Prosumers in 3 European cities [Operational Systems Paper]
- - Bijay Neupane
  - Laurynas Siksnys
  - et al.
- 2022
- e-Energy 2022
Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach
- - Nathalie Baracaldo Angel
  - Ali Anwar
  - et al.
- 2022
- arXiv
Accountable Federated Machine Learning in Government: Engineering and Management Insights
- - Dian Balta
  - Mahdi Sellami
  - et al.
- 2021
- ePart 2021
Knowledge- And Data-driven Services for Energy Systems using Graph Neural Networks
- - Francesco Fusco
  - Bradley Eck
  - et al.
- 2020
- Big Data 2020

Visit Google Scholar

Patents

- 10 Mar 2025
- US
- 12250150
Ai-based Compensation Of Resource Constrained Communication
- 29 May 2023
- US
- 11663228
Automated Management Of Data Transformation Flows Based On Semantics
- 17 Oct 2022
- US
- 11475332
Selecting Forecasting Models By Machine Learning Based On Analysis Of Model Robustness
- 03 Dec 2018
- US
- 10148303
Methods And Systems For Aquatic Infrastructure Recharge And Data Transfer

Projects

Adversarial Robustness Toolbox
Securing AI models with the Adversarial Robustness Toolbox
Federated Systems
Privacy Enhancing Technologies for Regulatory Compliance

Blog posts

DARPA and IBM are ensuring that anyone can protect their AI systems from hackers
News
Mike Murphy
07 Feb 2024
- AI
- Data and AI Security

Top collaborators

AR

Ambrish Rawat

Ambrish Rawat

Senior Research Scientist, AI Security and Privacy, Master Inventor

GZ

Giulio Zizzo

Giulio Zizzo

Staff Research Scientist

NB

Nathalie Baracaldo

Nathalie Baracaldo

Manager of AI Security and Privacy Solutions - Senior Research Scientist - Master Inventor, Ph.D.

BE

Bradley Eck

Bradley Eck

Senior Research Scientist & Manager - AI for Sustainable Industry