Events

2026

AI Safety and Security: Where Are We Now?

Jul 1, 2026 — Kraków, Poland

AI Safety and Security: Where Are We Now?

2025

Peacebuilding in the Age of AI and Digital Transformation

Nov 26, 2025 — Amman, Jordan

Peacebuilding in the Age of AI and Digital Transformation

Technical AI Safety & Security: From Alignment to Agentic Systems

Nov 18, 2025 — Tokyo, Japan

Open Problems and Challenges in Agentic Security

Oct 22, 2025 — Heathrow, London, UK

Technical AI Security & Safety: From Alignment to Agentic Systems

Oct 15, 2025 — Warsaw, Poland

The Safety of Operating Systems AI Agents: Formulations, Evaluations, and Certification

Sep 10, 2025 — Online

Progress in AI Safety and Security

Jul 1, 2025 — Berlin, Germany

Progress in AI Safety and Security

NYU: Technical AI Safety Research

Jun 2, 2025 — Online

Softserve: Foundations in AI Agents: Building & Prompting

Hackathon on AI Agents

May 21, 2025 — Online

NYUAD: Technical AI Safety Research

May 15, 2025 — Abu Dhabi, UAE

Softserve: AI Agents at Work. From QA to Beyond

Feb 20, 2025 — Online

Microsoft: From Adversarial Robustness to Agentic Safet

An invitation by Sunando Sengupta

Jan 30, 2025 — Online

SDAIA: AI Governance

Closed government session

Jan 26, 2025 — Online

SDAIA: AI Governance

2024

ELLIS: AI Safety Research

This is a talk to hosted by the Ukrainian Catholic University in Lviv as part of the ELLIS Lightning Talks

Sep 28, 2024 — Zoom

ELLIS: AI Safety Research

MBZUAI: AI Safety Research

An invitation by Prof Fahad Khan

Apr 19, 2024 — Abu Dhabi, UAE

MBZUAI: AI Safety Research

Oxford ORI: AI Safety Research

An invitation by Dr. Matias Mattamala, Dr. Alessandro Albini, and Dr. Jack Collins

Apr 12, 2024 — Oxford, UK

Oxford ORI: AI Safety Research

BAU: AI Safety Research

This is a talk to the Hamad Bin Khalifa University (HBKU). An Invitation by Dr Lama Affara.

Apr 2, 2024 — Online

HBKU: AI Safety Research

This is a talk at the ICT division of Hamad Bin Khalifa University (HBKU).

Mar 2, 2024 — Doha, Qatar

TAHAKOM: AI Safety Research

Tahakom is an AI startup based in Riyadh and owned by the Saudi Public Investment Fund.

Feb 15, 2024 12:00 AM — 12:00 AM Zoom

TAHAKOM: AI Safety Research

2023

ELLIS: Trustworthy AI

Dec 7, 2023 — Zoom

Intelmatix: Trustworthy Deep Learning

Nov 2, 2023 — Riyadh, Saudi Arabia

Intelmatix: Trustworthy Deep Learning

Kuwait University: Trustworthy and Safe Deep Learning

Oct 18, 2023 — Kuwait

Kuwait University: Trustworthy and Safe Deep Learning

ICMA: Certifying Deep Neural Networks at Scale

I am giving an inagural keynote speech on our work on scaling certification to deep networks.

Sep 26, 2023 — Zoom

Bristol University: Offline/Online Computationally Budgeted Continual Learning

My host was Dima Damen

Sep 5, 2023 — Bristol, United Kingdom

CVPR23: The Uncomfortable Reality: The Need for Budgeted Computation in Continual Learning

Jun 18, 2023 — Vancouver, Canada

Samsung: Computationally Budgeted Continual Learning

Apr 25, 2023 12:00 AM — 12:00 AM Cambridge, United Kingdom

CDT Oxford: Offline and Online Computationally Budgeted Continual Learning

Feb 17, 2023 — Information of Engineering Building, University of Oxford

2022

Adobe: Offline and Online Computationally Budgeted Continual Learning

Dec 6, 2022 — San Jose, California

Adobe: Offline and Online Computationally Budgeted Continual Learning

Raytheon: Deep Certification: From Empirical Robustness to Advances in Randomized Smoothing

Nov 16, 2022 12:00 AM — 12:00 AM Zoom

RSS: From Recent Advances in Video Understanding to Blind Spots in Deep Networks

Sep 26, 2022 12:00 AM — 12:00 AM Amman, Jordan

RSS: From Recent Advances in Video Understanding to Blind Spots in Deep Networks

KAUST: CRG Talks -- Challenges in Offline and Online Continual Learning

Sep 21, 2022 — Thuwal, Saudi Arabia

KAUST: CRG Talks -- Challenges in Offline and Online Continual Learning

KAUST: Generalized Certification Theory

Sep 20, 2022 — Thuwal, Saudi Arabia

KAUST: Generalized Certification Theory

Oxford Asia Pacific Society: Computer Vision and Machine Learning: Introduction, Applications, and Challenges

Feb 4, 2022 — Worcester College, Oxford University

Oxford Asia Pacific Society: Computer Vision and Machine Learning: Introduction, Applications, and Challenges

Oxford Brokkes: Recent Advances in Randomized Smoothing

Jan 30, 2022 — Jul 31, 2022 Zoom

Oxford Brokkes: Recent Advances in Randomized Smoothing

2021

DoD US: Trust Worthy AI -- Verified

Jun 24, 2021 — Zoom

DoD US: Trust Worthy AI -- Verified

2020

Huawei: From Adversarial Robustness to Randomized Smoothing

Dec 1, 2020 12:00 AM — Feb 1, 2020 12:00 AM Zoom

Huawei: From Adversarial Robustness to Randomized Smoothing

2019

Qualcomm AI: Analyzing a Block of Layers in Deep Neural Networks

Dec 16, 2019 — Amsterdam, Netherlands

Google: Analyzing a Block of Layers in Deep Neural Networks

Dec 2, 2019 — Zurich, Switzerland

Google: Analyzing a Block of Layers in Deep Neural Networks

PRIS: A Basket of Computer Vision Research Problems

Aug 7, 2019 12:00 AM — Aug 9, 2019 12:00 AM Dead Sea, Jordan

PRIS: A Basket of Computer Vision Research Problems

ECCV19: Optimization Approach to a Block of Layers and Derivative Free Optimization

Jul 7, 2019 — Jul 9, 2019 Odessa, Ukraine

ECCV19: Optimization Approach to a Block of Layers and Derivative Free Optimization

2018

CVPR18: Analytic Expressions for Probabilistic Moments of PL-DNN With Gaussian Input

Jun 18, 2018 — Jun 22, 2018 Salt Lake City, Utah, USA

CVPR18: Analytic Expressions for Probabilistic Moments of PL-DNN With Gaussian Input

KAUST OBD: High Order Tensor Formulation for Convolutional Sparse Coding

Feb 5, 2018 — Feb 7, 2018 Thuwal, Saudi Arabia

2017

CVPR17: FFTLasso: Large-Scale LASSO in the Fourier Domain

Jul 26, 2017 — Jul 27, 2016 Honolulu, Hawaii, USA

2016

ECCV16: Target Response Adaptation for Correlation Filter Tracking

Oct 1, 2016 — Oct 2, 2016 Amsterdam, The Netherlands

ECCV16: Target Response Adaptation for Correlation Filter Tracking