The Experts below are selected from a list of 6 Experts worldwide ranked by ideXlab platform
Mario Fritz - One of the best experts on this subject based on the ideXlab platform.
-
a 4 nt Author Attribute anonymity by adversarial training of neural machine translation
arXiv: Cryptography and Security, 2017Co-Authors: Rakshith Shetty, Bernt Schiele, Mario FritzAbstract:Text-based analysis methods allow to reveal privacy relevant Author Attributes such as gender, age and identify of the text's Author. Such methods can compromise the privacy of an anonymous Author even when the Author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called Adversarial Author Attribute Anonymity Neural Translation ($A^4NT$), to combat such text-based adversaries. We combine sequence-to-sequence language models used in machine translation and generative adversarial networks to obfuscate Author Attributes. Unlike machine translation techniques which need paired data, our method can be trained on unpaired corpora of text containing different Authors. Importantly, we propose and evaluate techniques to impose constraints on our $A^4NT$ to preserve the semantics of the input text. $A^4NT$ learns to make minimal changes to the input text to successfully fool Author Attribute classifiers, while aiming to maintain the meaning of the input. We show through experiments on two different datasets and three settings that our proposed method is effective in fooling the Author Attribute classifiers and thereby improving the anonymity of Authors.
-
a4nt Author Attribute anonymity by adversarial training of neural machine translation
USENIX Security Symposium, 2017Co-Authors: Rakshith Shetty, Bernt Schiele, Mario FritzAbstract:Text-based analysis methods enable an adversary to reveal privacy relevant Author Attributes such as gender, age and can identify the text's Author. Such methods can compromise the privacy of an anonymous Author even when the Author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called the Adversarial Author Attribute Anonymity Neural Translation ($\text{A}^{4}\text{NT}$), to combat such text-based adversaries. Unlike prior works on obfuscation, we propose a system that is fully automatic and learns to perform obfuscation entirely from the data. This allows us to easily apply the $\text{A}^{4}\text{NT}$ system to obfuscate different Author Attributes. We propose a sequence-to-sequence language model, inspired by machine translation, and an adversarial training framework to design a system which learns to transform the input text to obfuscate the Author Attributes without paired data. We also propose and evaluate techniques to impose constraints on our $\text{A}^{4}\text{NT}$ model to preserve the semantics of the input text. $\text{A}^{4}\text{NT}$ learns to make minimal changes to the input to successfully fool Author Attribute classifiers, while preserving the meaning of the input text. Our experiments on two datasets and three settings show that the proposed method is effective in fooling the Attribute classifiers and thus improves the anonymity of Authors.
Rakshith Shetty - One of the best experts on this subject based on the ideXlab platform.
-
a 4 nt Author Attribute anonymity by adversarial training of neural machine translation
arXiv: Cryptography and Security, 2017Co-Authors: Rakshith Shetty, Bernt Schiele, Mario FritzAbstract:Text-based analysis methods allow to reveal privacy relevant Author Attributes such as gender, age and identify of the text's Author. Such methods can compromise the privacy of an anonymous Author even when the Author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called Adversarial Author Attribute Anonymity Neural Translation ($A^4NT$), to combat such text-based adversaries. We combine sequence-to-sequence language models used in machine translation and generative adversarial networks to obfuscate Author Attributes. Unlike machine translation techniques which need paired data, our method can be trained on unpaired corpora of text containing different Authors. Importantly, we propose and evaluate techniques to impose constraints on our $A^4NT$ to preserve the semantics of the input text. $A^4NT$ learns to make minimal changes to the input text to successfully fool Author Attribute classifiers, while aiming to maintain the meaning of the input. We show through experiments on two different datasets and three settings that our proposed method is effective in fooling the Author Attribute classifiers and thereby improving the anonymity of Authors.
-
a4nt Author Attribute anonymity by adversarial training of neural machine translation
USENIX Security Symposium, 2017Co-Authors: Rakshith Shetty, Bernt Schiele, Mario FritzAbstract:Text-based analysis methods enable an adversary to reveal privacy relevant Author Attributes such as gender, age and can identify the text's Author. Such methods can compromise the privacy of an anonymous Author even when the Author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called the Adversarial Author Attribute Anonymity Neural Translation ($\text{A}^{4}\text{NT}$), to combat such text-based adversaries. Unlike prior works on obfuscation, we propose a system that is fully automatic and learns to perform obfuscation entirely from the data. This allows us to easily apply the $\text{A}^{4}\text{NT}$ system to obfuscate different Author Attributes. We propose a sequence-to-sequence language model, inspired by machine translation, and an adversarial training framework to design a system which learns to transform the input text to obfuscate the Author Attributes without paired data. We also propose and evaluate techniques to impose constraints on our $\text{A}^{4}\text{NT}$ model to preserve the semantics of the input text. $\text{A}^{4}\text{NT}$ learns to make minimal changes to the input to successfully fool Author Attribute classifiers, while preserving the meaning of the input text. Our experiments on two datasets and three settings show that the proposed method is effective in fooling the Attribute classifiers and thus improves the anonymity of Authors.
Bernt Schiele - One of the best experts on this subject based on the ideXlab platform.
-
a 4 nt Author Attribute anonymity by adversarial training of neural machine translation
arXiv: Cryptography and Security, 2017Co-Authors: Rakshith Shetty, Bernt Schiele, Mario FritzAbstract:Text-based analysis methods allow to reveal privacy relevant Author Attributes such as gender, age and identify of the text's Author. Such methods can compromise the privacy of an anonymous Author even when the Author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called Adversarial Author Attribute Anonymity Neural Translation ($A^4NT$), to combat such text-based adversaries. We combine sequence-to-sequence language models used in machine translation and generative adversarial networks to obfuscate Author Attributes. Unlike machine translation techniques which need paired data, our method can be trained on unpaired corpora of text containing different Authors. Importantly, we propose and evaluate techniques to impose constraints on our $A^4NT$ to preserve the semantics of the input text. $A^4NT$ learns to make minimal changes to the input text to successfully fool Author Attribute classifiers, while aiming to maintain the meaning of the input. We show through experiments on two different datasets and three settings that our proposed method is effective in fooling the Author Attribute classifiers and thereby improving the anonymity of Authors.
-
a4nt Author Attribute anonymity by adversarial training of neural machine translation
USENIX Security Symposium, 2017Co-Authors: Rakshith Shetty, Bernt Schiele, Mario FritzAbstract:Text-based analysis methods enable an adversary to reveal privacy relevant Author Attributes such as gender, age and can identify the text's Author. Such methods can compromise the privacy of an anonymous Author even when the Author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called the Adversarial Author Attribute Anonymity Neural Translation ($\text{A}^{4}\text{NT}$), to combat such text-based adversaries. Unlike prior works on obfuscation, we propose a system that is fully automatic and learns to perform obfuscation entirely from the data. This allows us to easily apply the $\text{A}^{4}\text{NT}$ system to obfuscate different Author Attributes. We propose a sequence-to-sequence language model, inspired by machine translation, and an adversarial training framework to design a system which learns to transform the input text to obfuscate the Author Attributes without paired data. We also propose and evaluate techniques to impose constraints on our $\text{A}^{4}\text{NT}$ model to preserve the semantics of the input text. $\text{A}^{4}\text{NT}$ learns to make minimal changes to the input to successfully fool Author Attribute classifiers, while preserving the meaning of the input text. Our experiments on two datasets and three settings show that the proposed method is effective in fooling the Attribute classifiers and thus improves the anonymity of Authors.
