A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models

Zhongliang Guo, Weiye Li, Yifei Qian, Ognjen Arandjelovic, Lei Fang
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:901-909, 2024.

Abstract

In this paper, we tackle the challenge of white-box false positive adversarial attacks on contrastive loss based offline handwritten signature verification models. We propose a novel attack method that treats the attack as a style transfer between closely related but distinct writing styles. To guide the generation of deceptive images, we introduce two new loss functions that enhance the attack success rate by perturbing the Euclidean distance between the embedding vectors of the original and synthesized samples, while ensuring minimal perturbations by reducing the difference between the generated image and the original image. Our method demonstrates state-of-the-art performance in white-box attacks on contrastive loss based offline handwritten signature verification models, as evidenced by our experiments. The key contributions of this paper include a novel false positive attack method, two new loss functions, effective style transfer in handwriting styles, and superior performance in white-box false positive attacks compared to other white-box attack methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v238-guo24a, title = { A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models }, author = {Guo, Zhongliang and Li, Weiye and Qian, Yifei and Arandjelovic, Ognjen and Fang, Lei}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {901--909}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/guo24a/guo24a.pdf}, url = {https://proceedings.mlr.press/v238/guo24a.html}, abstract = { In this paper, we tackle the challenge of white-box false positive adversarial attacks on contrastive loss based offline handwritten signature verification models. We propose a novel attack method that treats the attack as a style transfer between closely related but distinct writing styles. To guide the generation of deceptive images, we introduce two new loss functions that enhance the attack success rate by perturbing the Euclidean distance between the embedding vectors of the original and synthesized samples, while ensuring minimal perturbations by reducing the difference between the generated image and the original image. Our method demonstrates state-of-the-art performance in white-box attacks on contrastive loss based offline handwritten signature verification models, as evidenced by our experiments. The key contributions of this paper include a novel false positive attack method, two new loss functions, effective style transfer in handwriting styles, and superior performance in white-box false positive attacks compared to other white-box attack methods. } }
Endnote
%0 Conference Paper %T A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models %A Zhongliang Guo %A Weiye Li %A Yifei Qian %A Ognjen Arandjelovic %A Lei Fang %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-guo24a %I PMLR %P 901--909 %U https://proceedings.mlr.press/v238/guo24a.html %V 238 %X In this paper, we tackle the challenge of white-box false positive adversarial attacks on contrastive loss based offline handwritten signature verification models. We propose a novel attack method that treats the attack as a style transfer between closely related but distinct writing styles. To guide the generation of deceptive images, we introduce two new loss functions that enhance the attack success rate by perturbing the Euclidean distance between the embedding vectors of the original and synthesized samples, while ensuring minimal perturbations by reducing the difference between the generated image and the original image. Our method demonstrates state-of-the-art performance in white-box attacks on contrastive loss based offline handwritten signature verification models, as evidenced by our experiments. The key contributions of this paper include a novel false positive attack method, two new loss functions, effective style transfer in handwriting styles, and superior performance in white-box false positive attacks compared to other white-box attack methods.
APA
Guo, Z., Li, W., Qian, Y., Arandjelovic, O. & Fang, L.. (2024). A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models . Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:901-909 Available from https://proceedings.mlr.press/v238/guo24a.html.

Related Material