ICSE 2026
Sun 12 - Sat 18 April 2026 Rio de Janeiro, Brazil
Sun 12 Apr 2026 16:45 - 17:00 at Oceania II - Trustworthy AI Systems

This study introduces a novel approach to uncovering and assessing biases in text-to-image models by employing adversarial prompts. Our strategy involves several key steps: (1) selecting words indicative of bias from existing literature; (2) crafting a set of original and noisy prompts, where noisy refers to prompts modified with positive or negative connotations; (3) applying these prompts across various text-to-image models; (4) annotating the generated images for demographic attributes such as gender and skin tone; and (5) analyzing and comparing the representation of demographic groups in images produced from both original and modified prompts. Our findings are derived from a dataset of 54 adversarial prompts tested on 6 text-to-image models, resulting on 324 generated images. The analysis revealed that even slight modifications to prompts could significantly influence the portrayal of demographic groups, often amplifying biases.

Sun 12 Apr

Displayed time zone: Brasilia, Distrito Federal, Brazil change

16:00 - 17:30
Trustworthy AI SystemsRAIE at Oceania II
16:00
45m
Keynote
From Biased to Trustworthy AI: Responsible Agentic Software Engineering Beyond Code
RAIE
Rashina Hoda Monash University
16:45
15m
Talk
An Adversarial-Attack Approach to Assess Bias in Text-to-Image Models
RAIE
Keya Gangadharan Penn State University, Nathalia Nascimento Pennsylvania State University, Paulo Alencar University of Waterloo, Myron David Peixoto Federal University of Alagoas, Audrey Vasconcelos Federal University of Alagoas (UFAL), Davy Baia Federal University of Alagoas, Baldoino Fonseca Federal University of Alagoas (UFAL)
17:00
15m
Talk
Reliable SOC LLM Agent with Workflow Generation
RAIE
Shohei Mitani Georgetown University, Siddharth Yadav Virginia Tech, Shinichiro Matsuo Georgetown University, Eric Burger Virginia Tech
17:15
15m
Talk
Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text
RAIE