Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference
Adversarial reprogramming allows repurposing a machine-learning model to perform a different task. For example, a model trained to recognize animals can be reprogrammed to recognize digits by embedding an adversarial program in the digit images provided as input. Recent work has shown that adversarial reprogramming may not only be used to abuse machine-learning models provided as a service, but also beneficially, to improve transfer learning when training data is scarce. However, the factors affecting its success are still largely unexplained. In this work, we develop a first-order linear model of adversarial reprogramming to show that its success inherently depends on the size of the average input gradient, which grows when input gradients are more aligned, and when inputs have higher dimensionality. The results of our experimental analysis, involving fourteen distinct reprogramming tasks, show that the above factors are correlated with the success and the failure of adversarial reprogramming.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adversarial Reprogramming Revisited
Adversarial reprogramming, introduced by Elsayed, Goodfellow, and Sohl-Dickstein, seeks to repurpose a neural network to perform a different task, by manipulating its input without modifying its weights. We prove that tw…
Reprogramming Language Models for Molecular Representation Learning
Recent advancements in transfer learning have made it a promising approach for domain adaptation via transfer of learned representations. This is especially when relevant when alternate tasks have limited samples of well…
Dictionary LearningDomain Adaptationmolecular representationRepresentation Learning+1WARP: Word-level Adversarial ReProgramming
Transfer learning from pretrained language models recently became the dominant approach for solving many NLP tasks. A common approach to transfer learning for multiple tasks that maximize parameter sharing trains one or …
Language ModelingLanguage ModellingTransfer LearningWord EmbeddingsCross-modal Adversarial Reprogramming
With the abundance of large-scale deep learning models, it has become possible to repurpose pre-trained networks for new tasks. Recent works on adversarial reprogramming have shown that it is possible to repurpose neural…
ClassificationGeneral Classificationimage-classificationImage ClassificationAdversarial Reprogramming of Text Classification Neural Networks
Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network. An adversary in such an attack sce…
ClassificationGeneral Classificationtext-classificationText Classification