Dr. Adel Bibi

Senior Fellow at Oxford University and R&D Distinguished Advisor at Softserve with over a decade expertise in AI, machine learning, Safety, and Security particularly in the space of LLMs, VLMs, and Agentic systems

Research Expertise

AI Safety
AI Security
Machine Learning

About

Highly accomplished AI researcher with extensive experience in machine learning, deep learning, and AI safety. Proven ability to lead research teams, secure funding, and publish in top-tier conferences. Expertise in developing innovative AI solutions and advising on AI adoption.

Publications

The Visual Object Tracking VOT2015 Challenge Results
2015 IEEE International Conference on Computer Vision Workshop (ICCVW)
2015
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
Lecture Notes in Computer Science
2018
Target Response Adaptation for Correlation Filter Tracking
Lecture Notes in Computer Science
2016
Can Large Language Model Agents Simulate Human Trust Behavior?
Advances in Neural Information Processing Systems 37
2024
Universal In-Context Approximation By Prompting Fully Recurrent Models
Advances in Neural Information Processing Systems 37
2024
In Defense of Sparse Tracking: Circulant Sparse Tracker
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
2016
Real-Time Evaluation in Online Continual Learning: A New Hope
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2023
Computationally Budgeted Continual Learning: What Does Matter?
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2023
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Advances in Neural Information Processing Systems 37
2024
3D Part-Based Sparse Tracker with Automatic Synchronization and Registration
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
2016
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
Advances in Neural Information Processing Systems 37
2024
Comment on the Paper Titled ’The Origin of Quantum Mechanical Statistics: Insights from Research on Human Language’ (arXiv preprint arXiv:2407.14924, 2024)
Unknown Venue
2024
Multi-template Scale-Adaptive Kernelized Correlation Filters
2015 IEEE International Conference on Computer Vision Workshop (ICCVW)
2015
On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspective
IEEE Transactions on Pattern Analysis and Machine Intelligence
2023
Rethinking open source generative AI: open washing and the EU AI Act
The 2024 ACM Conference on Fairness, Accountability, and Transparency
2024
DeformRS: Certifying Input Deformations with Randomized Smoothing
Proceedings of the AAAI Conference on Artificial Intelligence
2022
Rethinking Clustering for Robustness
Proceedings of the British Machine Vision Conference 2021
2021
Combating Adversaries with Anti-adversaries
Proceedings of the AAAI Conference on Artificial Intelligence
2022
Analytic Expressions for Probabilistic Moments of PL-DNN with Gaussian Input
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
2018
AI Platforms Security
AI-EDU Arxiv
2025
High Order Tensor Formulation for Convolutional Sparse Coding
2017 IEEE International Conference on Computer Vision (ICCV)
2017
Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing
2019 International Conference on Robotics and Automation (ICRA)
2019
Local Color Mapping Combined with Color Transfer for Underwater Image Enhancement
2019 IEEE Winter Conference on Applications of Computer Vision (WACV)
2019
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
Findings of the Association for Computational Linguistics: EMNLP 2024
2024
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
2023 IEEE/CVF International Conference on Computer Vision (ICCV)
2023
CoTMSD: Leveraging Chain-of-Thought for Multi-modal Sarcasm Detection
Data Intelligence
2025
Safety Risks in Fine-Tuning Large Language Models
Introduction to Foundation Models
2025
Metric Learning for Robust High-Level Representations against Adversarial Attacks
2024 IEEE International Conference on Software System and Information Processing (ICSSIP)
2024
Label Delay in Online Continual Learning
Advances in Neural Information Processing Systems 37
2024
Constrained Clustering: General Pairwise and Cardinality Constraints
IEEE Access
2023
Efficient Lifelong Model Evaluation in an Era of Rapid Progress
Advances in Neural Information Processing Systems 37
2024
Don’t FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
2023
FFTLasso: Large-Scale LASSO in the Fourier Domain
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
2017
RANCER: Non-Axis Aligned Anisotropic Certification with Randomized Smoothing
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
2023
Deep and Physics-Informed Neural Networks as a Substitute for Finite Element Analysis
2024 9th International Conference on Machine Learning Technologies (ICMLT)
2024
Blood pressure monitoring during anesthesia induction using PPG morphology features and machine learning
PLOS ONE
2023
Model sensitivity analysis on arxiv
Unknown Venue
2018
FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging
Lecture Notes in Computer Science
2024
On Pretraining Data Diversity for Self-Supervised Learning
Lecture Notes in Computer Science
2024
Towards Secure Federated Learning for Energy Forecasting under Adversarial Attacks
Unknown Venue
2025
Scalable and Interpretable Mixture of Experts Models in Machine Learning: Foundations, Applications, and Challenges
Unknown Venue
2025
e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
2021
Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation
Lecture Notes in Computer Science
2025
ARXİV SƏNƏDLƏRİNİN MÜHAFİZƏXANALARDA MÜHAFİZƏ QAYDALARI
ADMİU Elmi Əsərlər
2025
Detecting Errors through Ensembling Prompts (DEEP): An End-to-End LLM Framework for Detecting Factual Errors
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
2024
Deep Learning in Python: Training a Neural Network with Keras
Unknown Venue
2019
Responsible Machine Learning
Machine Learning Evaluation
2024
SimCS: Simulation for Domain Incremental Online Continual Segmentation
Proceedings of the AAAI Conference on Artificial Intelligence
2024
Diversified Dynamic Routing for Vision Tasks
Lecture Notes in Computer Science
2023
A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control
Proceedings of the AAAI Conference on Artificial Intelligence
2020
Gabor Layers Enhance Network Robustness
Lecture Notes in Computer Science
2020
No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
2024
Certified machine learning: A posteriori error estimation for physics-informed neural networks
2022 International Joint Conference on Neural Networks (IJCNN)
2022
Open data from the first and second observing runs of Advanced LIGO and Advanced Virgo
SoftwareX
2021
Diverse ensembles for active learning
Twenty-first international conference on Machine learning - ICML '04
2004
Robust Low-Overhead Control of DER Reactive Power Under Adversarial Attacks and Uncertainty
ICC 2024 - IEEE International Conference on Communications
2024
Materials Horizons 2022 Outstanding Paper Award
Materials Horizons
2023
Announcement of the Neural Networks Best Paper Award
Neural Networks
2023
Calibration Attack: Adversarial Attacks Against Model Calibration
Unknown Venue
2023
Stealing Machine Learning Models: Attacks and Countermeasures for Generative Adversarial Networks
Annual Computer Security Applications Conference
2021
Appraising machine learning classifiers for discriminating rotor condition in 50W–12V operational wind turbine for maximizing wind energy production through feature extraction and selection process
Frontiers in Energy Research
2022
Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning
Nature Communications
2021

Education

King Abdullah University of Science and Technology

PhD / 2020

King Abdullah University of Science and Technology

MSc / 2016

Experience

University of Oxford

Senior Research Fellow / December, 2021November, 2023

Postdoctoral Research Fellow / October, 2020November, 2021

Department of Engineering Science University of Oxford

Senior Researcher in Machine Learning (G9: eqv. spinal point to Associate Professor) / March, 2023September

Leading a group of 4-5 PhD students and 1-2 postdocs with a research focus on AI safety provable certication methods against Model Hijacking Fairness among others. Selected Accomplishments: Three of my students have successfully defended their Oxford PhD (Francisco Eiras Csaba Botos and Ameya Prabhu); won the UK AISI Systemic AI Safety Grant (300000) won the Google Gemma 2 Academic Award 2024 (20000); notable Area Chair Award for NeurIPS23; Senior Area Chair at NeurIPS24 chairing an Oral session; 2 best paper awards in 2024; 1 Highlight paper in CVPR23; 1 Oral paper in CVPR24; and 1 spotlight in ICLR23; a total of 17 papers accepted in 2024 in ICML NeurIPS AAAI ECCV and other venues. The total money raised in research funding is 850000 with another 1000000 that is approved and now is subject to contract.

Senior Research Associate in Machine Learning (G8) / December, 2021February, 2023

I co-supervised PhD students with Philip Torr on topics spanning robustness and continual learning at scale. I also mentored recently joining postdocs in the group. Selected Accomplishments: Awarded the Amazon Research Award (20212022); selected as an ELLIS member; won the Highlighted Reviewer Award of ICLR 2022 (awarded to 8.7% of 6207 reviewers); 1 Oral paper in AAAI22; nominated as an Area Chair for AAAI23.

Postdoctoral Research Assistant in Machine Learning (G7) / October, 2020December, 2021

I worked with Philip Torr focusing on empirical robustness and probabilistic certication with randomized smoothing of deep models. Selected Accomplishments: Awarded the prestigious Junior Fellowship at Kellogg College Oxford; awarded the KAUST-Oxford CRG grant (1.05M); published 3 papers in TMLR PAMI and UAI.

Kellogg College University of Oxford

Research Member of the Common Room / September, 2024September

None

Junior Research Fellow / October, 2021August, 2024

This is a prestigious three-years fellowship recognizing the impact of my research

Intel Labs Munich Germany

PhD Research Intern / June, 2018December, 2018

PhD Research Intern in Vision and Optimization: I worked on studying the theoretical connection between feed forward layers and stochastic optimization algorithms. One paper published as a result in ICLR19. I gave 2 oral presentations during the internship

Softserve

R&D Distinguished Advisor / August, 2024Present

SoftServe is a billion-dollar tech services company. I am building SoftServe’s new research program on Agentic AI. Several products are launched withsignificant revenue.

Links & Social Media

Join Adel on NotedSource!
Join Now

At NotedSource, we believe that professors, post-docs, scientists and other researchers have deep, untapped knowledge and expertise that can be leveraged to drive innovation within companies. NotedSource is committed to bridging the gap between academia and industry by providing a platform for collaboration with industry and networking with other researchers.

For industry, NotedSource identifies the right academic experts in 24 hours to help organizations build and grow. With a platform of thousands of knowledgeable PhDs, scientists, and industry experts, NotedSource makes connecting and collaborating easy.

For academic researchers such as professors, post-docs, and Ph.D.s, NotedSource provides tools to discover and connect to your colleagues with messaging and news feeds, in addition to the opportunity to be paid for your collaboration with vetted partners.

Expert Institutions
NotedSource has experts from Stanford University
Expert institutions using NotedSource include Oxfort University
Experts from McGill have used NotedSource to share their expertise
University of Chicago experts have used NotedSource
MIT researchers have used NotedSource
Proudly trusted by
Microsoft uses NotedSource for academic partnerships
Johnson & Johnson academic research projects on NotedSource
ProQuest (Clarivate) uses NotedSource as their industry academia platform
Slamom consulting engages academics for research collaboration on NotedSource
Omnicom and OMG find academics on notedsource
Unilever research project have used NotedSource to engage academic experts

Connect with researchers and scientists like Dr. Adel Bibi on NotedSource to help your company with innovation, research, R&D, L&D, and more.