Feb. 13, 2024, 5:48 a.m. | Zhongliang Guo Weiye Li Yifei Qian Ognjen Arandjelovi\'c Lei Fang

cs.CV updates on arXiv.org arxiv.org

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 …

adversarial adversarial attacks attacks box challenge cs.ai cs.cv false loss novel offline paper positive style style transfer transfer verification writing

Research Scholar (Technical Research)

@ Centre for the Governance of AI | Hybrid; Oxford, UK

HPC Engineer (x/f/m) - DACH

@ Meshcapade GmbH | Remote, Germany

Senior Analytics Engineer (Retail)

@ Lightspeed Commerce | Toronto, Ontario, Canada

Data Scientist II, BIA GPS India Operations

@ Bristol Myers Squibb | Hyderabad

Analytics Engineer

@ Bestpass | Remote

Senior Analyst - Data Management

@ Marsh McLennan | Mumbai - Hiranandani