Partially Recentralization Softmax Loss for Vision-Language Models Robustness

As Large Language Models make a breakthrough in natural language processing tasks (NLP), multimodal technique becomes extremely popular. However, it has been shown that multimodal NLP are vulnerable to adversarial attacks, where the outputs of a model can be dramatically changed by a perturbation to the input. While several defense techniques have been proposed both in computer vision and NLP models, the multimodal robustness of models have not been fully explored. In this paper, we study the adversarial robustness provided by modifying loss function of pre-trained multimodal models, by restricting top K softmax outputs. Based on the evaluation and scoring, our experiments show that after a fine-tuning, adversarial robustness of pre-trained models can be significantly improved, against popular attacks. Further research should be studying, such as output diversity, generalization and the robustness-performance trade-off of this kind of loss functions. Our code will be available after this paper is accepted

Distribution-restrained Softmax Loss for the Model Robustness

Recently, the robustness of deep learning models has received widespread attention, and various methods for improving model robustness have been proposed, including adversarial training, model architecture modification, design of loss functions, certified defenses, and so on. However, the principle of the robustness to attacks is still not fully understood, also the related research is still not sufficient. Here, we have identified a significant factor that affects the robustness of models: the distribution characteristics of softmax values for non-real label samples. We found that the results after an attack are highly correlated with the distribution characteristics, and thus we proposed a loss function to suppress the distribution diversity of softmax. A large number of experiments have shown that our method can improve robustness without significant time consumption.

Towards interpreting computer vision based on transformation invariant optimization

Interpreting how does deep neural networks (DNNs) make predictions is a vital field in artificial intelligence, which hinders wide applications of DNNs. Visualization of learned representations helps we humans understand the vision of DNNs. In this work, visualized images that can activate the neural network to the target classes are generated by back-propagation method. Here, rotation and scaling operations are applied to introduce the transformation invariance in the image generating process, which we find a significant improvement on visualization effect. Finally, we show some cases that such method can help us to gain insight into neural networks.