Covert and Potent: A Weather-Camouflaged Backdoor Attacks on Self-Supervised Learning

Yang Wei, Yonghao Yang, Bo Liu, Bin Xiao

Abstract: Self-supervised learning is widely applied across various domains due to its advantage of learning data representations without the need for labels. However, recent research shows that backdoor attacks on self-supervised learning are achievable by coupling benign features with trigger features without manipulating labels. Existing methods, however, suffer from poor trigger disguise. When designing triggers, more emphasis is placed on attack strength rather than on disguising the triggers, which makes these triggers easily detectable through manual inspection or preprocessing methods. Therefore, we propose a camouflaged self-supervised backdoor attack method from the perspective of visual disguise. Specifically, we design triggers by embedding variable adverse weather information to achieve visual camouflage, which can bypass certain defence methods to some extent. Additionally, since our proposed camouflaged triggers have a global nature, they achieve more efficient backdoor attack capabilities. Experiments demonstrate that our method achieves attack success rates of 83.4% on the CIFAR-100 dataset and 44.8% on the ImageNet-100 dataset, surpassing existing state-of-the-art methods by 14.6% and 24.4%, respectively. At the same time, our method exhibits better stealthiness.