4 papers · 1 filter
SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models
Justus Westerhoff, Erblina Purelku, Jakob Hackstein +4
Typographic attacks exploit the interplay between text and visual content in multimodal foundation models, causing misclassifications when misleading text is embedded within images…
Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
Lorenz Hufe, Constantin Venhoff, Erblina Purelku +3
Typographic attacks exploit multi-modal systems by injecting text into images, leading to targeted misclassifications, malicious content generation and even Vision-Language Model j…
Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
Sonia Joseph, Praneet Suresh, Lorenz Hufe +7
Robust tooling and publicly available pre-trained models have helped drive recent advances in mechanistic interpretability for language models. However, similar progress in vision…
Steering CLIP's vision transformer with sparse autoencoders
Sonia Joseph, Praneet Suresh, Ethan Goldfarb +6
While vision models are highly capable, their internal mechanisms remain poorly understood -- a challenge which sparse autoencoders (SAEs) have helped address in language, but whic…