论文标题
动态随机合奏与对抗性稳健彩票子网
Dynamic Stochastic Ensemble with Adversarial Robust Lottery Ticket Subnetworks
论文作者
论文摘要
对抗攻击被认为是CNN的内在脆弱性。为攻击而设计的防御策略已被困在对抗性攻击防御武器竞赛中，反映了攻击和防守之间的失衡。动态防御框架（DDF）最近根据随机集成模型更改了被动安全状态。子网的多样性是DDF中的重要问题，可以通过不同网络之间的对抗性可传递性有效地评估。受到剩余比率各不相比的子网之间的较差的对抗性可转移性的启发，我们提出了一种实现动态随机合奏防御策略的方法。我们发现了从不同基本结构和稀疏性绘制的可靠彩票子网之间的对抗性转移多样性。实验结果表明，我们的方法通过可转移的多样性实现了更好和清洁的识别精度，这将降低攻击的可靠性。
Adversarial attacks are considered the intrinsic vulnerability of CNNs. Defense strategies designed for attacks have been stuck in the adversarial attack-defense arms race, reflecting the imbalance between attack and defense. Dynamic Defense Framework (DDF) recently changed the passive safety status quo based on the stochastic ensemble model. The diversity of subnetworks, an essential concern in the DDF, can be effectively evaluated by the adversarial transferability between different networks. Inspired by the poor adversarial transferability between subnetworks of scratch tickets with various remaining ratios, we propose a method to realize the dynamic stochastic ensemble defense strategy. We discover the adversarial transferable diversity between robust lottery ticket subnetworks drawn from different basic structures and sparsity. The experimental results suggest that our method achieves better robust and clean recognition accuracy by adversarial transferable diversity, which would decrease the reliability of attacks.
