Skip to content

Publications

Selected publications are listed below. A full and frequently updated list is available on Google Scholar.

Latest Papers

ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI
Mohadeseh Mollapour, Koorosh Aslansefat, Zeinab Dehghani, Bhupesh Kumar Mishra, Tejal Shah, Zhibao Mian
arXiv (Cornell University), 2026. DOI / source

When Words Move Markets: Interpretable Behavioural and Robustness Analysis of LLMs for Financial Sentiment Reasoning via Local Perturbation Explanations
Sania Verma, Koorosh Aslansefat, Joyjit Chatterjee, Akash Marar, Anu Mehra, Aisha Ekundayo
Lecture notes in computer science, 2026. DOI / source

Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answering
Louis Donaldson, Connor Walker, Koorosh Aslansefat, Yiannis Papadopoulos
arXiv (Cornell University), 2026. DOI / source

Risk Assessments for Evasive Emergency Maneuvers in Autonomous Vehicles
Aliasghar Arab, Milad Khaleghi, Koorosh Aslansefat
arXiv (Cornell University), 2026. DOI / source

A Multi-Modal Dataset for Ground Reaction Force Estimation Using Consumer Wearable Sensors
Parvin Ghaffarzadeh, Debarati Bhunia Chakraborty, Koorosh Aslansefat, Ali Dostan, Yiannis Papadopoulos
Scientific Data, 2026. DOI / source

Exploring the Impact of Skin Color on Skin Lesion Segmentation
Kuniko Paxton, Medina Kapo, Amila Akagić, Koorosh Aslansefat, Dhavalkumar Thakker, Yiannis Papadopoulos
arXiv (Cornell University), 2026. DOI / source

EcoFair: Trustworthy and Energy-Aware Routing for Privacy-Preserving Vertically Partitioned Medical Inference
Mostafa Anoosha, Dhavalkumar Thakker, Kuniko Paxton, Koorosh Aslansefat, Bhupesh Kumar Mishra, Baseer Ahmad, Rameez Raja Kureshi
arXiv (Cornell University), 2026. DOI / source

Evaluating a Multi-Agent Voice-Enabled Smart Speaker for Care Homes: A Safety-Focused Framework
Zeinab Dehghani, Rameez Raja Kureshi, Koorosh Aslansefat, Faezeh Alsadat Abedi, Dhavalkumar Thakker, Lisa Greaves, Bhupesh Kumar Mishra, Baseer Ahmad, et al.
arXiv (Cornell University), 2026. DOI / source

No Trust Without Assurance: Establishing a Shared Vocabulary for AI Risk Domains
David Molyneux, Dhavalkumar Thakker, Koorosh Aslansefat, Kevin Pimbblet, S Pengelly, Zac Baker-Amaral
SSRN Electronic Journal, 2026. DOI / source

Enhancing Fairness in Skin Lesion Classification for Medical Diagnosis Using Prune Learning
Kuniko Paxton, Koorosh Aslansefat, Dhavalkumar Thakker, Yiannis Papadopoulos, Tanaya Maslekar
IEEE Journal of Biomedical and Health Informatics, 2026. DOI / source

Leveraging Generative Models to Produce Safety Artifacts: A Proof-of-Concept for Autonomous Driving
Zhibao Mian, Koorosh Aslansefat
Lecture notes in networks and systems, 2026. DOI / source

HybridVFL: Disentangled Feature Learning for Edge-Enabled Vertical Federated Multimodal Classification
Mostafa Anoosha, Zeinab Dehghani, Kuniko Paxton, Koorosh Aslansefat, Dhavalkumar Thakker
Conference Paper, 2025. DOI / source

Skewness-Guided Pruning of Multimodal Swin Transformers for Federated Skin Lesion Classification on Edge Devices
Kuniko Paxton, Koorosh Aslansefat, Dhavalkumar Thakker, Yiannis Papadopoulos
Conference Paper, 2025. DOI / source

RAGuard: A Novel Approach for In-Context Safe Retrieval Augmented Generation for LLMs
Connor Walker, Koorosh Aslansefat, Mohammed Naveed Akram, Yiannis Papadopoulos
Lecture notes in computer science, 2025. DOI / source Cited by 2 in OpenAlex.

Safer Skin Lesion Classification with Global Class Activation Probability Map Evaluation and SafeML
Kuniko Paxton, Koorosh Aslansefat, Amila Akagić, Dhavalkumar Thakker, Yiannis Papadopoulos
Lecture notes in computer science, 2025. DOI / source

Automatically updated from OpenAlex using ORCID 0000-0001-9318-8177. Google Scholar remains available as the public profile: Koorosh Aslansefat.

Selected Papers

SafeLLM: Domain-Specific Safety Monitoring for Large Language Models
Walker, C., Rothon, C., Aslansefat, K., Papadopoulos, Y., and Dethlefs, N.
IOP Journal of Physics, 2875(1), 1-19, 2024.

Measuring AI Fairness in a Continuum Maintaining Nuances
Paxton, K., Aslansefat, K., Thakker, D., and Papadopoulos, Y.
IEEE Internet Computing, 28(5), 11-19, 2024.

Explaining black boxes with a SMILE
Aslansefat, K., Hashemian, M., Walker, M., Akram, M. N., Sorokos, I., and Papadopoulos, Y.
IEEE Software, 41(1), 87-97, 2023.

A Review of the Applications of Explainable Machine Learning for Lithium-Ion Batteries
Faraji Niri, M., Aslansefat, K., Haghi, S., Hashemian, M., Daub, R., and Marco, J.
Energies, 16(17), 6360, 2023.

Toward improving confidence in autonomous vehicle software
Aslansefat, K., Kabir, S., Abdullatif, A., Vasudevan, V., and Papadopoulos, Y.
IEEE Computer, 54(8), 66-76, 2021.

SafeDrones: Real-Time Reliability Evaluation of UAVs
Aslansefat, K., Nikolaou, P., Walker, M., et al.
International Symposium on Model-Based Safety and Assessment, Springer, 2022.

SafeML: Safety Monitoring of Machine Learning Classifiers
Aslansefat, K., Sorokos, I., Whiting, D., et al.
International Symposium on Model-Based Safety and Assessment, Springer LNCS 12297, 2020.

Profiles