An Empirical Evaluation of Adversarial Robustness under Transfer Learning
In this work, we evaluate adversarial robustness in the context of transfer learning from a source trained on CIFAR 100 to a target network trained on CIFAR 10. Specifically, we study the effects of using robust optimisation in the source and target networks. This allows us to identify transfer learning strategies under which adversarial defences are successfully retained, in addition to revealing potential vulnerabilities. We study the extent to which features learnt by a fast gradient sign method (FGSM) and its iterative alternative (PGD) can preserve their defence properties against black and white-box attacks under three different transfer learning strategies. We find that using PGD examples during training on the source task leads to more general robust features that are easier to transfer. Furthermore, under successful transfer, it achieves 5.2% more accuracy against white-box PGD attacks than suitable baselines. Overall, our empirical evaluations give insights on how well adversarial robustness under transfer learning can generalise.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessTransfer LearningSimilar Papers 제목 키워드 기반
Transfer of Adversarial Robustness Between Perturbation Types
We study the transfer of adversarial robustness of deep neural networks between different perturbation types. While most work on adversarial examples has focused on $L_\infty$ and $L_2$-bounded perturbations, these do no…
Adversarial RobustnessTwo Sides of the Same Coin: White-box and Black-box Attacks for Transfer Learning
Transfer learning has become a common practice for training deep learning models with limited labeled data in a target domain. On the other hand, deep models are vulnerable to adversarial attacks. Though transfer learnin…
Transfer LearningUnderstanding the Robustness of Graph Neural Networks against Adversarial Attacks
Recent studies have shown that graph neural networks (GNNs) are vulnerable to adversarial attacks, posing significant challenges to their deployment in safety-critical scenarios. This vulnerability has spurred a growing …
Adversarial RobustnessThe Diversity Metrics of Sub-models based on SVD of Jacobians for Ensembles Adversarial Robustness
Transferability of adversarial samples under different CNN models is not only one of the metrics indicators for evaluating the performance of adversarial examples, but also an important research direction in the defense …
Adversarial RobustnessAttributeAttribute ExtractionDimensionality Reduction+1Robustness of SAM: Segment Anything Under Corruptions and Beyond
Segment anything model (SAM), as the name suggests, is claimed to be capable of cutting out any object and demonstrates impressive zero-shot transfer performance with the guidance of prompts. However, there is currently …
Style Transfer