Looking From the Future: Multi-order Iterations Can Enhance Adversarial Attack Transferability
This work addresses the challenge of making adversarial attacks more effective across different models, which is crucial for security testing and robustness evaluation in machine learning, though it appears incremental as it builds upon existing iteration-based attack methods.
The paper tackles the problem of improving adversarial attack transferability by proposing a novel sequence optimization concept called Looking From the Future (LFF), which refines initial optimization choices using future information, resulting in methods that greatly enhance transferability as demonstrated on the ImageNet1k dataset across multiple tasks.
Various methods try to enhance adversarial transferability by improving the generalization from different perspectives. In this paper, we rethink the optimization process and propose a novel sequence optimization concept, which is named Looking From the Future (LFF). LFF makes use of the original optimization process to refine the very first local optimization choice. Adapting the LFF concept to the adversarial attack task, we further propose an LFF attack as well as an MLFF attack with better generalization ability. Furthermore, guiding with the LFF concept, we propose an $LLF^{\mathcal{N}}$ attack which entends the LFF attack to a multi-order attack, further enhancing the transfer attack ability. All our proposed methods can be directly applied to the iteration-based attack methods. We evaluate our proposed method on the ImageNet1k dataset by applying several SOTA adversarial attack methods under four kinds of tasks. Experimental results show that our proposed method can greatly enhance the attack transferability. Ablation experiments are also applied to verify the effectiveness of each component. The source code will be released after this paper is accepted.