6 papers
AI-to-AI Code Reviews of GitHub Pull Requests
Niruthiha Selvanayagam, Taher A. Ghaleb
AI coding agents are increasingly integrated into software development workflows, operating on both sides of the pull-request (PR) process: AI authoring agents create or modify PRs…
Is GPT-4o mini Blinded by its Own Safety Filters? Exposing the Multimodal-to-Unimodal Bottleneck in Hate Speech Detection
Niruthiha Selvanayagam, Ted Kurti
As Large Multimodal Models (LMMs) become integral to daily digital life, understanding their safety architectures is a critical problem for AI Alignment. This paper presents a syst…
FragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments
Astha Mehta, Niruthiha Selvanayagam, Cedric Lam +10
An attacker can split a malicious goal into sub-prompts that each look benign on their own and only become harmful in combination. Existing LLM safety benchmarks evaluate prompts o…
MLmisFinder: A Specification and Detection Approach of Machine Learning Service Misuses
Hadil Ben Amor, Niruthiha Selvanayagam, Manel Abdellatif +2
Machine Learning (ML) cloud services, offered by leading providers such as Amazon, Google, and Microsoft, enable the integration of ML components into software systems without buil…
Self-Admitted Technical Debt in LLM Software: An Empirical Comparison with ML and Non-ML Software
Niruthiha Selvanayagam, Taher A. Ghaleb, Manel Abdellatif
Self-admitted technical debt (SATD), referring to comments flagged by developers that explicitly acknowledge suboptimal code or incomplete functionality, has received extensive att…
Multidimensional Analysis of Specific Language Impairment Using Unsupervised Learning Through PCA and Clustering
Niruthiha Selvanayagam
Specific Language Impairment (SLI) affects approximately 7 percent of children, presenting as isolated language deficits despite normal cognitive abilities, sensory systems, and su…