6 papers
Out-of-the-box: Black-box Causal Attacks on Object Detectors
Melane Navaratnarajah, David A. Kelly, Hana Chockler
Adversarial perturbations are a useful way to expose vulnerabilities in object detectors. Existing perturbation methods are frequently white-box, architecture specific and use a lo…
Fuzz Smarter, Not Harder: Towards Greener Fuzzing with GreenAFL
Ayse Irmak Ercevik, Aidan Dakhama, Melane Navaratnarajah +2
Fuzzing has become a key search-based technique for software testing, but continuous fuzzing campaigns consume substantial computational resources and generate significant carbon f…
Defining and Quantifying Creative Behavior in Popular Image Generators
Aditi Ramaswamy, Hana Chockler, Melane Navaratnarajah
Creativity of generative AI models has been a subject of scientific debate in the last years, without a conclusive answer. In this paper, we study creativity from a practical persp…
3D ReX: Causal Explanations in 3D Neuroimaging Classification
Melane Navaratnarajah, Sophie A. Martin, David A. Kelly +2
Explainability remains a significant problem for AI models in medical imaging, making it challenging for clinicians to trust AI-driven predictions. We introduce 3D ReX, the first c…
It's a Feature, Not a Bug: Measuring Creative Fluidity in Image Generators
Aditi Ramaswamy, Melane Navaratnarajah, Hana Chockler
With the rise of freely available image generators, AI-generated art has become the centre of a series of heated debates, one of which concerns the concept of human creativity. Can…
You Only Explain Once
David A. Kelly, Hana Chockler, Daniel Kroening +4
In this paper, we propose a new black-box explainability algorithm and tool, YO-ReX, for efficient explanation of the outputs of object detectors. The new algorithm computes explan…