100 citations · 145 across the 24 of their papers we have counts for
27 papers
Evaluating Inference-Time Defenses Against Package Hallucination in LLM-Generated Code
Alberick Euraste Djire, Iyiola E. Olatunji, Melissa Tessa +3
LLMs are increasingly used for code generation, yet they frequently hallucinate non-existent software packages, creating exploitable entry points into the software supply chain. We…
Do Not Copy/Paste: Soft Barriers for Copying in AI-Assisted Programming
Iyiola E. Olatunji, Alberick Euraste Djire, Jacques Klein +1
Copying a function from a chat window into an editor takes less than a second. For many uses of AI coding tools, that speed is the point; in settings such as programming education,…
Memorization Diagnostics for Code LLMs Should be Scale-Aware
Prateek Kumar Rajput, Abdoul Aziz Bonkoungou, Alberick Euraste Djiré +6
The extent to which large language models for code rely on memorization over genuine understanding remains highly debated. While current literature frequently reports widespread me…
Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation
Marco Alecci, Francesco Marchiori, Iyiola Emmanuel Olatunji +2
While automated content-moderation systems have become essential for screening harmful content at scale, conventional task-specific classifiers often provide limited policy cov- er…
Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency
Matthew L. Smith, Jonathan P. Shock, Samuel T. Segun +2
While scaling laws govern aggregate large language model performance, no scaling law has linked factual recall to both model size and training-data composition. We evaluated 38 mod…
Evaluation Drift in LLM Personality Induction: Are We Moving the Goalpost?
Prateek Rajput, Yewei Song, Iyiola E. Olatunji +2
Can large language models reliably express a human-like personality, or are they merely mimicking surface cues without a stable underlying profile? To investigate this, we induce p…
Correctness isnt Efficiency: Runtime Memory Divergence in LLM-Generated Code
Prateek Rajput, Yewei Song, Abdoul Aziz Bonkoungou +4
Large language models (LLMs) can generate programs that pass unit tests, but passing tests does not guarantee reliable runtime behavior. We find that different correct solutions to…
Towards Sensitivity-Aware Language Models
Dren Fazlija, Iyiola E. Olatunji, Daniel Kudenko +1
With LLMs increasingly deployed in corporate data management, it is crucial to ensure that these models do not leak sensitive information. In the context of corporate data manageme…
How Secure is Secure Code Generation? Adversarial Prompts Put LLM Defenses to the Test
Melissa Tessa, Iyiola E. Olatunji, Aicha War +2
Recent secure code generation methods, using vulnerability-aware fine-tuning, prefix-tuning, and prompt optimization, claim to prevent LLMs from producing insecure code. However, t…
From Rookie to Pro: Social Engineering LLMs for Automated Vulnerability Exploitation in Enterprise Software
Moustapha Awwalou Diouf, Maimouna Tamah Diao, Iyiola Emmanuel Olatunji +6
LLMs democratize software engineering by enabling non-programmers to create applications, but this same accessibility fundamentally undermines security assumptions that have guided…
Dynamic Stability of LLM-Generated Code
Prateek Rajput, Abdoul Aziz Bonkoungou, Yewei Song +4
Current evaluations of LLMs for code generation emphasize functional correctness, overlooking the fact that functionally correct solutions can differ significantly in algorithmic c…
Characterizing Build Compromises Through Vulnerability Disclosure Analysis
Maimouna Tamah Diao, Moustapha Awwalou Diouf, Iyiola Emmanuel Olatunji +4
The software build process transforms source code into deployable artifacts, representing a critical yet vulnerable stage in software development. Build infrastructure security pos…
Beyond Real Faces: Synthetic Datasets Can Achieve Reliable Recognition Performance without Privacy Compromise
Paweł 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…
Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation
Xunzhu Tang, Iyiola Emmanuel Olatunji, Tiezhu Sun +2
LLMs demonstrate surface-level fluency in code generation but struggle with structured reasoning tasks requiring correctness and semantic alignment. While Chain-of-Thought (CoT) pr…
Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs)
Iyiola E. Olatunji, Franziska Boenisch, Jing Xu +1
Large Language Models (LLMs) are increasingly integrated with graph-structured data for tasks like node classification, a domain traditionally dominated by Graph Neural Networks (G…
SCOOTER: A Human Evaluation Framework for Unrestricted Adversarial Examples
Dren Fazlija, Monty-Maximilian Zühlke, Johanna Schrader +4
Unrestricted adversarial attacks aim to fool computer vision models without being constrained by -norm bounds to remain imperceptible to humans, for example, by changing an…
DP-GPL: Differentially Private Graph Prompt Learning
Jing Xu, Franziska Boenisch, Iyiola Emmanuel Olatunji +1
Graph Neural Networks (GNNs) have shown remarkable performance in various applications. Recently, graph prompt learning has emerged as a powerful GNN training paradigm, inspired by…
Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives
Vincent Hanke, Tom Blanchard, Franziska Boenisch +3
While open Large Language Models (LLMs) have made significant progress, they still fall short of matching the performance of their closed, proprietary counterparts, making the latt…
Does Black-box Attribute Inference Attacks on Graph Neural Networks Constitute Privacy Risk?
Iyiola E. Olatunji, Anmar Hizber, Oliver Sihlovec +1
Graph neural networks (GNNs) have shown promising results on real-life datasets and applications, including healthcare, finance, and education. However, recent studies have shown t…
Private Graph Extraction via Feature Explanations
Iyiola E. Olatunji, Mandeep Rathee, Thorben Funke +1
Privacy and interpretability are two important ingredients for achieving trustworthy machine learning. We study the interplay of these two aspects in graph machine learning through…
Releasing Graph Neural Networks with Differential Privacy Guarantees
Iyiola E. Olatunji, Thorben Funke, Megha Khosla
With the increasing popularity of graph neural networks (GNNs) in several sensitive applications like healthcare and medicine, concerns have been raised over the privacy aspects of…
Achieving differential privacy for -nearest neighbors based outlier detection by data partitioning
Jens Rauch, Iyiola E. Olatunji, Megha Khosla
When applying outlier detection in settings where data is sensitive, mechanisms which guarantee the privacy of the underlying data are needed. The -nearest neighbors (-NN) al…
A Review of Anonymization for Healthcare Data
Iyiola E. Olatunji, Jens Rauch, Matthias Katzensteiner +1
Mining health data can lead to faster medical decisions, improvement in the quality of treatment, disease prevention, reduced cost, and it drives innovative solutions within the he…
Membership Inference Attack on Graph Neural Networks
Iyiola E. Olatunji, Wolfgang Nejdl, Megha Khosla
Graph Neural Networks (GNNs), which generalize traditional deep neural networks on graph data, have achieved state-of-the-art performance on several graph analytical tasks. We focu…