Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision
A reinforcement-learning black-box attack fools vision models with fewer queries than earlier methods.
The paper proposes RIBA, a black-box adversarial attack that borrows reinforcement-learning ideas to optimize perturbations against non-differentiable computer-vision models. Compared with prior attacks, it reports 25.4% fewer median queries to attack a ResNet-18 on CIFAR-10 and 22.5% fewer to fool a ViT-B/16 on ImageNet. The authors also say RIBA can match white-box attack performance against an adversarially trained model. No real-world incident is described.
- RIBA optimizes black-box perturbations using reinforcement-learning ideas.
- It used 25.4% fewer median queries against ResNet-18 on CIFAR-10.
- It used 22.5% fewer median queries against ViT-B/16 on ImageNet.
- Authors say it can match white-box results on an adversarially trained model.
- Tags
- adversarial-attackblack-boxreinforcement-learningcomputer-visionresnetvision-transformerimagenetcifar-10
From the original article
1 min read at arxiv.orgNeural networks, both convolution or transformer based, are essential for modern computer vision systems. However, they are vulnerable to small perturbations, almost imperceptible to humans, which significantly alter the model's prediction. These adversarial attacks are often considered to be a significant threat to the implementation of neural networks in safety-critical applications.
By Florian Krone · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.