Iyiola E. Olatunji

works on

adversarial attacks 1 content safety 1 foundation models 1 image moderation 1 robustness evaluation 1

From the 1 of 18 linked papers with an AI index.

activity

20242026

most citedPredictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency

4 citations · 4 across the 6 of their papers we have counts for

collaborators

Showing cs.CVShow all

2 papers · 1 filter

cs.CV2026

SCOOTER: A Human Evaluation Framework for Unrestricted Adversarial Examples

Dren Fazlija, Monty-Maximilian ZÃ¼hlke, Johanna Schrader +4

Unrestricted adversarial attacks aim to fool computer vision models without being constrained by $ℓ_{p}$ -norm bounds to remain imperceptible to humans, for example, by changing an…

cs.CV2025

Beyond Real Faces: Synthetic Datasets Can Achieve Reliable Recognition Performance without Privacy Compromise

PaweÅ Borsukiewicz, Fadi Boutros, Iyiola E. Olatunji +4

The deployment of facial recognition systems has created an ethical dilemma: achieving high accuracy requires massive datasets of real faces collected without consent, leading to d…