Pith. sign in

REVIEW

SpecFormer: Guarding Vision Transformer Robustness via Maximum Singular Value Penalization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.03317 v2 pith:UNYAQM75 submitted 2024-01-02 cs.CV cs.LG

classification cs.CVcs.LG
keywords adversarialattacksspecformervisionvitsboundsmaximummodel
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Vision Transformers (ViTs) are increasingly used in computer vision due to their high performance, but their vulnerability to adversarial attacks is a concern. Existing methods lack a solid theoretical basis, focusing mainly on empirical training adjustments. This study introduces SpecFormer, tailored to fortify ViTs against adversarial attacks, with theoretical underpinnings. We establish local Lipschitz bounds for the self-attention layer and propose the Maximum Singular Value Penalization (MSVP) to precisely manage these bounds By incorporating MSVP into ViTs' attention layers, we enhance the model's robustness without compromising training efficiency. SpecFormer, the resulting model, outperforms other state-of-the-art models in defending against adversarial attacks, as proven by experiments on CIFAR and ImageNet datasets. Code is released at https://github.com/microsoft/robustlearn.

Discussion (0). Continue with ORCID to comment.

Pith tools