1.4k citations · 4.4k across the 74 of their papers we have counts for
84 papers
A New Kind of Adversarial Example: Measuring the Human-Model Gap, and Its Relationship to OOD Detection
Ali Borji
Almost all adversarial attacks add an imperceptible perturbation to fool a model. We instead study the opposite: a large, clearly visible perturbation that causes the model to keep…
Addressing a fundamental limitation in deep vision models: lack of spatial attention
Ali Borji
The primary aim of this manuscript is to underscore a significant limitation in current deep learning models, particularly vision models. Unlike human vision, which efficiently sel…
Key-Value Transformer
Ali Borji
Transformers have emerged as the prevailing standard solution for various AI tasks, including computer vision and natural language processing. The widely adopted Query, Key, and Va…
A Categorical Archive of ChatGPT Failures
Ali Borji
Large language models have been demonstrated to be valuable in different fields. ChatGPT, developed by OpenAI, has been trained using massive amounts of data and simulates human co…
Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes
Ali Borji
The ability of image and video generation models to create photorealistic images has reached unprecedented heights, making it difficult to distinguish between real and fake images…
Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object Classification
Ali Borji
Test sets are an integral part of evaluating models and gauging progress in object recognition, and more broadly in computer vision and AI. Existing test sets for object recognitio…