Hadi M. Dolatabadi

According to our database, Hadi M. Dolatabadi authored at least 16 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization.

Alexander Long, Chamin Hewa Koneputugodage, Thalaiyasingam Ajanthan, Yan Zuo, Gil Avraham, Violetta Shevchenko, Hadi Mohaghegh Dolatabadi, Sameera Ramasinghe

CoRR, May, 2026

NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training.

Hadi Mohaghegh Dolatabadi, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Chamin Hewa Koneputugodage, Shamane Siriwardhana, Violetta Shevchenko, Karol Pajak, James Snewin, Gil Avraham, Alexander Long

CoRR, March, 2026

SENTINEL: Stagewise Integrity Verification for Pipeline Parallel Decentralized Training.

Hadi Mohaghegh Dolatabadi, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Chamin Hewa Koneputugodage, Gil Avraham, Yan Zuo, Violetta Shevchenko, Alexander Long

CoRR, March, 2026

AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism.

Thalaiyasingam Ajanthan, Sameera Ramasinghe, Gil Avraham, Hadi Mohaghegh Dolatabadi, Chamin Hewa Koneputugodage, Violetta Shevchenko, Yan Zuo, Alexander Long

CoRR, January, 2026

2025

Exploiting Inter-Sample Information for Long-Tailed Out-of-Distribution Detection.

Nimeshika Udayangani, Hadi M. Dolatabadi, Sarah M. Erfani, Christopher Leckie

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025

Round Trip Translation Defence Against Large Language Model Jailbreaking Attacks.

Canaan Yung, Hadi Mohaghegh Dolatabadi, Sarah M. Erfani, Christopher Leckie

Proceedings of the Trends and Applications in Knowledge Discovery and Data Mining, 2025

2024

The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Models.

Hadi M. Dolatabadi, Sarah M. Erfani, Christopher Leckie

Proceedings of the IEEE Conference on Secure and Trustworthy Machine Learning, 2024

Be Persistent: Towards a Unified Solution for Mitigating Shortcuts in Deep Learning.

Hadi M. Dolatabadi, Sarah M. Erfani, Christopher Leckie

Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024

2023

Adversarial Coreset Selection for Efficient Robust Training.

Hadi M. Dolatabadi, Sarah M. Erfani, Christopher Leckie

Int. J. Comput. Vis., December, 2023

2022

A Novel Perspective on Robustness in Deep Learning.

Hadi Mohaghegh Dolatabadi

PhD thesis, 2022

ℓ _∞-Robustness and Beyond: Unleashing Efficient Adversarial Training.

Hadi M. Dolatabadi, Sarah M. Erfani, Christopher Leckie

Proceedings of the Computer Vision - ECCV 2022, 2022

COLLIDER: A Robust Training Framework for Backdoor Data.

Hadi M. Dolatabadi, Sarah M. Erfani, Christopher Leckie

Proceedings of the Computer Vision - ACCV 2022, 2022

2020

Black-box Adversarial Example Generation with Normalizing Flows.

Hadi M. Dolatabadi, Sarah M. Erfani, Christopher Leckie

CoRR, 2020

AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows.

Hadi Mohaghegh Dolatabadi, Sarah M. Erfani, Christopher Leckie

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Invertible Generative Modeling using Linear Rational Splines.

Hadi Mohaghegh Dolatabadi, Sarah M. Erfani, Christopher Leckie

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Deterministic Design of Toeplitz Matrices With Small Coherence Based on Weyl Sums.

Hadi Mohaghegh Dolatabadi, Arash Amini

IEEE Signal Process. Lett., 2019