paper-with-me

홈 › Papers

Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference

2021-08-26 · Yang Zheng, Xiaoyi Feng, Zhaoqiang Xia, Xiaoyue Jiang, Ambra Demontis, Maura Pintor, Battista Biggio, Fabio Roli

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.

📄 PDF Abstract BibTeX arXiv:2108.11673

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningTransfer Learning

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

Adversarial Reprogramming Revisited

2022-06-07 · Matthias Englert, Ranko Lazic

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

2020-12-07 · Ria Vinod, Pin-Yu Chen, Payel Das

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+1

WARP: Word-level Adversarial ReProgramming

2021-01-01 · ACL 2021 5 · Karen Hambardzumyan, Hrant Khachatrian, Jonathan May

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 Embeddings

Cross-modal Adversarial Reprogramming

2021-02-15 · Paarth Neekhara, Shehzeen Hussain, Jinglong Du, Shlomo Dubnov 외

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 Classification

Adversarial Reprogramming of Text Classification Neural Networks

2018-09-06 · IJCNLP 2019 11 · Paarth Neekhara, Shehzeen Hussain, Shlomo Dubnov, Farinaz Koushanfar

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