Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detection

Adelani, David Ifeoluwa; Mai, Haotian; Fang, Fuming; Nguyen, Huy H.; Yamagishi, Junichi; Echizen, Isao

doi:10.48550/arxiv.1907.09177

Cited by 4 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ Adelani et al, 2019] showed how to create and detect fake online reviews of a pre-specified sentiment. In contrast, we do not generate fake reviews but only generate misleading justifications for review classifications.…”

Section: Heuristic-based Detectionmentioning

confidence: 99%

“…In particular, ML techniques have been used to detect lies in human-interaction, eg. [Aroyo et al, 2018].…”

Section: Heuristic-based Detectionmentioning

confidence: 99%

“…Online media struggle against the plague of "fake news", and e-commerce sites spend considerable effort in detecting deceptive product reviews. For example, marketing strategies exist that consider the creation of fake reviews to make products appear better or to provide false claims about product quality [Adelani et al, 2019].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deceptive AI Explanations: Creation and Detection

Schneider

Meske²,

Vlachos

2022

Proceedings of the 14th International Conference on Agents and Artificial Intelligence

View full text Add to dashboard Cite

Artificial intelligence comes with great opportunities and but also great risks. We investigate to what extent deep learning can be used to create and detect deceptive explanations that either aim to lure a human into believing a decision that is not truthful to the model or provide reasoning that is nonfaithful to the decision. Our theoretical insights show some limits of deception and detection in the absence of domain knowledge. For empirical evaluation, we focus on text classification. To create deceptive explanations, we alter explanations originating from GradCAM, a state-of-art technique for creating explanations in neural networks. We evaluate the effectiveness of deceptive explanations on 200 participants. Our findings indicate that deceptive explanations can indeed fool humans. Our classifier can detect even seemingly minor attempts of deception with accuracy that exceeds 80% given sufficient domain knowledge encoded in the form of training data.

show abstract

Section: Heuristic-based Detectionmentioning

confidence: 99%

“…In particular, ML techniques have been used to detect lies in human-interaction, eg. [Aroyo et al, 2018].…”

Section: Heuristic-based Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Deceptive AI Explanations: Creation and Detection

Schneider

Meske²,

Vlachos

2022

Proceedings of the 14th International Conference on Agents and Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…It is not uncommon to involve humans in the detection process. For instance, to detect fake reviews [1] the GLTR method estimates word probabilities that are then presented to a human for further investigation. However, there are also fully automatic methods like GROVER [21] show-cased for fake news detection.…”

Section: Related Workmentioning

confidence: 99%

AI Forensics: Did the Artificial Intelligence System Do It? Why?

Schneider¹,

Breitinger²

2020

Preprint

View full text Add to dashboard Cite

In an increasingly autonomous manner AI systems make decisions impacting our daily life. Their actions might cause accidents, harm or, more generally, violate regulations -either intentionally or not. Thus, AI systems might be considered suspects for various events. Therefore, it is essential to relate particular events to an AI, its owner and its creator. Given a multitude of AI systems from multiple manufactures, potentially, altered by their owner or changing through self-learning, this seems non-trivial. This paper discusses how to identify AI systems responsible for incidents as well as their motives that might be "malicious by design". In addition to a conceptualization, we conduct two case studies based on reinforcement learning and convolutional neural networks to illustrate our proposed methods and challenges. Our cases illustrate that "catching AI systems" seems often far from trivial and requires extensive expertise in machine learning. Legislative measures that enforce mandatory information to be collected during operation of AI systems as well as means to uniquely identify systems might facilitate the problem.

show abstract

“…The contributions in this study include: (1) the exploration of major beliefs expressed by people about the surrounding world using an automatic computational pipeline, (2) a novel alternative to topic modeling allowing latent semantic dimensions to be represented by generated phrases rather than lists of words, (3) the demonstration that latent dimensions represented as generated phrases can be more interpretable than representing dimensions with their most prevalent words as is common in traditional topic modeling. Ad- ditionally, we also (4) explore different approaches for modifying autoregressive transformer models to generate texts conditioned on a vector rather than leading tokens or with prompting texts as in other related works (Pilault et al 2020;Wolf et al 2019;Zhang et al 2020;Adelani et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Modeling Latent Dimensions of Human Beliefs

Giorgi

Clifton

et al. 2022

ICWSM

View full text Add to dashboard Cite

How we perceive our surrounding world impacts how we live in and react to it. In this study, we propose LaBel (Latent Beliefs Model), an alternative to topic modeling that uncovers latent semantic dimensions from transformer-based embeddings and enables their representation as generated phrases rather than word lists. We use LaBel to explore the major beliefs that humans have about the world and other prevalent domains, such as education or parenting. Although human beliefs have been explored in previous works, our proposed model helps automate the exploring process to rely less on human experts, saving time and manual efforts, especially when working with large corpus data. Our approach to LaBel uses a novel modification of autoregressive transformers to effectively generate texts conditioning on a vector input format. Differently from topic modeling methods, our generated texts (e.g. “the world is truly in your favor”) are discourse segments rather than word lists, which helps convey semantics in a more natural manner with full context. We evaluate LaBel dimensions using both an intrusion task as well as a classification task of identifying categories of major beliefs in tweets finding greater accuracies than popular topic modeling approaches.

show abstract

Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detection

Cited by 4 publications

References 19 publications

Deceptive AI Explanations: Creation and Detection

Deceptive AI Explanations: Creation and Detection

AI Forensics: Did the Artificial Intelligence System Do It? Why?

Modeling Latent Dimensions of Human Beliefs

Contact Info

Product

Resources

About