Poster · Sydney

The Adversarial Gait: Detecting Visual Adversarial Attacks against Vision-Language Models via Self-Targeted Gradient Characterization

Name: The Adversarial Gait: Detecting Visual Adversarial Attacks against Vision-Language Models via Self-Targeted Gradient Characterization
Start: 2026-12-09T10:00:00+11:00
End: 2026-12-09T13:00:00+11:00
Location: Hall 1-4, ICC Sydney

When: Wed 9 Dec 2026, 10:00–13:00 AEDT
Where: Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session: Sydney Poster Session 3
Authors: Mauricio Byrd Victorica, Ezzeldin Shereen, György Dán
Organisations: KTH Royal Institute of Technology, Alan Turing Institute
QRS classification: Language models, Computer vision, Safety, fairness and privacy

Open in schedule Official page