Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910287330803712 |
|---|---|
| author | Siciliano, Federico Maiano, Luca Papa, Lorenzo Baccini, Federica Amerini, Irene Silvestri, Fabrizio |
| author_facet | Siciliano, Federico Maiano, Luca Papa, Lorenzo Baccini, Federica Amerini, Irene Silvestri, Fabrizio |
| contents | Fake news detection models are critical to countering disinformation but can be manipulated through adversarial attacks. In this position paper, we analyze how an attacker can compromise the performance of an online learning detector on specific news content without being able to manipulate the original target news. In some contexts, such as social networks, where the attacker cannot exert complete control over all the information, this scenario can indeed be quite plausible. Therefore, we show how an attacker could potentially introduce poisoning data into the training data to manipulate the behavior of an online learning method. Our initial findings reveal varying susceptibility of logistic regression models based on complexity and attack type. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_15228 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It Siciliano, Federico Maiano, Luca Papa, Lorenzo Baccini, Federica Amerini, Irene Silvestri, Fabrizio Machine Learning Computation and Language Cryptography and Security Fake news detection models are critical to countering disinformation but can be manipulated through adversarial attacks. In this position paper, we analyze how an attacker can compromise the performance of an online learning detector on specific news content without being able to manipulate the original target news. In some contexts, such as social networks, where the attacker cannot exert complete control over all the information, this scenario can indeed be quite plausible. Therefore, we show how an attacker could potentially introduce poisoning data into the training data to manipulate the behavior of an online learning method. Our initial findings reveal varying susceptibility of logistic regression models based on complexity and attack type. |
| title | Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It |
| topic | Machine Learning Computation and Language Cryptography and Security |
| url | https://arxiv.org/abs/2312.15228 |