ProTIP: Probabilistic robustness verification on text-to-image diffusion models against stochastic perturbation
Abstract Text-to-Image (T2I) Diffusion Models (DMs) excel at creating high-quality images
from text descriptions but, like many deep learning models, suffer from robustness issues …
from text descriptions but, like many deep learning models, suffer from robustness issues …
Challenges and opportunities in text generation explainability
The necessity for interpretability in natural language processing (NLP) has risen alongside
the growing prominence of large language models. Among the myriad tasks within NLP, text …
the growing prominence of large language models. Among the myriad tasks within NLP, text …
[PDF][PDF] Challenges and Opportunities in Text Generation Explainability
M El-Assady - arXiv preprint arXiv:2405.08468, 2024 - academia.edu
The necessity for interpretability in natural language processing (NLP) has risen alongside
the growing prominence of large language models. Among the myriad tasks within NLP, text …
the growing prominence of large language models. Among the myriad tasks within NLP, text …
Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey
Text-to-Image (T2I) Diffusion Models (DMs) have garnered widespread attention for their
impressive advancements in image generation. However, their growing popularity has …
impressive advancements in image generation. However, their growing popularity has …
Generative Inpainting for Shapley-Value-Based Anomaly Explanation
J Tritscher, P Lissmann, M Wolf, A Krause… - World Conference on …, 2024 - Springer
Feature relevance explanations currently constitute the most used type of explanation in
anomaly detection related tasks such as cyber security and fraud detection. Recent works …
anomaly detection related tasks such as cyber security and fraud detection. Recent works …