Boost Adversarial Transferability by Uniform Scale and Mix Mask Method

Adversarial examples generated from surrogate models often possess the ability to deceive other black-box models, a property known as transferability. Recent research has focused on enhancing adversarial transferability, with input transformation being one of the most effective approaches. However, existing input transformation methods suffer from two issues. Firstly, certain methods, such as the Scale-Invariant Method, employ exponentially decreasing scale invariant parameters that decrease the adaptability in generating effective adversarial examples across multiple scales. Secondly, most mixup methods only linearly combine candidate images with the source image, leading to reduced features blending effectiveness. To address these challenges, we propose a framework called Uniform Scale and Mix Mask Method (US-MM) for adversarial example generation. The Uniform Scale approach explores the upper and lower boundaries of perturbation with a linear factor, minimizing the negative impact of scale copies. The Mix Mask method introduces masks into the mixing process in a nonlinear manner, significantly improving the effectiveness of mixing strategies. Ablation experiments are conducted to validate the effectiveness of each component in US-MM and explore the effect of hyper-parameters. Empirical evaluations on standard ImageNet datasets demonstrate that US-MM achieves an average of 7% better transfer attack success rate compared to state-of-the-art methods.

Understanding CNNs from excitations

For instance-level explanation, in order to reveal the relations between high-level semantics and detailed spatial information, this paper proposes a novel cognitive approach to neural networks, which named PANE. Under the guidance of PANE, a novel saliency map representation method, named IOM, is proposed for CNN-like models. We make the comparison with eight state-of-the-art saliency map representation methods. The experimental results show that IOM far outperforms baselines. The work of this paper may bring a new perspective to understand deep neural networks.