paper-with-me

Papers

RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts

2023-01-01 · CVPR 2023 1 · Han Liu, Yuhao Wu, Shixuan Zhai, Bo Yuan, Ning Zhang

The field of text-to-image generation has made remarkable strides in creating high-fidelity and photorealistic images. As this technology gains popularity, there is a growing concern about its potential security risks. However, there has been limited exploration into the robustness of these models from an adversarial perspective. Existing research has primarily focused on untargeted settings, and lacks holistic consideration for reliability (attack success rate) and stealthiness (imperceptibility). In this paper, we propose RIATIG, a reliable and imperceptible adversarial attack against text-to-image models via inconspicuous examples. By formulating the example crafting as an optimization process and solving it using a genetic-based method, our proposed attack can generate imperceptible prompts for text-to-image generation models in a reliable way. Evaluation of six popular text-to-image generation models demonstrates the efficiency and stealthiness of our attack in both white-box and black-box settings. To allow the community to build on top of our findings, we've made the artifacts available.

📄 PDF Abstract BibTeX

Code (1)

wustl-cspl/riatig 공식 구현 pytorch

Tasks

Adversarial AttackAdversarial TextImage GenerationText to Image GenerationText-to-Image Generation

Similar Papers 제목 키워드 기반

Adversarial Training against Location-Optimized Adversarial Patches

2020-05-05 · Sukrut Rao, David Stutz, Bernt Schiele

Deep neural networks have been shown to be susceptible to adversarial examples -- small, imperceptible changes constructed to cause mis-classification in otherwise highly accurate image classifiers. As a practical altern…

Imperceptible Adversarial Attacks on Tabular Data

2019-11-08 · Vincent Ballet, Xavier Renard, Jonathan Aigrain, Thibault Laugel 외

Security of machine learning models is a concern as they may face adversarial attacks for unwarranted advantageous decisions. While research on the topic has mainly been focusing on the image domain, numerous industrial …

BIG-bench Machine Learning

Imperceptible Adversarial Attack via Invertible Neural Networks

2022-11-28 · Zihan Chen, Ziyue Wang, JunJie Huang, Wentao Zhao 외

Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples. Though visual imperceptibility is the d…

Adversarial Attack

Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery Detection

2020-10-29 · Yongwei Wang, Xin Ding, Li Ding, Rabab Ward 외

Recently, generative adversarial networks (GANs) can generate photo-realistic fake facial images which are perceptually indistinguishable from real face photos, promoting research on fake face detection. Though fake face…

Adversarial AttackFace Detection

SAIF: Sparse Adversarial and Imperceptible Attack Framework

2022-12-14 · Tooba Imtiaz, Morgan Kohler, Jared Miller, Zifeng Wang 외

Adversarial attacks hamper the decision-making ability of neural networks by perturbing the input signal. The addition of calculated small distortion to images, for instance, can deceive a well-trained image classificati…

Decision Makingimage-classificationImage Classification