Corpus ID: 168169824

Defending Against Neural Fake News

@article{Zellers2019DefendingAN,
  title={Defending Against Neural Fake News},
  author={Rowan Zellers and Ari Holtzman and Hannah Rashkin and Yonatan Bisk and Ali Farhadi and Franziska Roesner and Yejin Choi},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.12616}
}
Recent progress in natural language generation has raised dual-use concerns. [...] Key Result We conclude by discussing ethical issues regarding the technology, and plan to release Grover publicly, helping pave the way for better detection of neural fake news.Expand
Viable Threat on News Reading: Generating Biased News Using Natural Language Models
TLDR
A threat model is used to demonstrate that the publicly available language models can reliably generate biased news content based on an input original news and it is shown that a large number of high-quality biased news articles can be generated using controllable text generation. Expand
MALCOM: Generating Malicious Comments to Attack Neural Fake News Detection Models
TLDR
Malcom, an end-to-end adversarial comment generation framework, is developed that can successfully mislead five of the latest neural detection models to always output targeted real and fake news labels. Expand
The Limitations of Stylometry for Detecting Machine-Generated Fake News
TLDR
Though stylometry can successfully prevent impersonation by identifying text provenance, it fails to distinguish legitimate LM applications from those that introduce false information, highlighting the need for non-stylometry approaches in detecting machine-generated misinformation. Expand
Are We Safe Yet? The Limitations of Distributional Features for Fake News Detection
TLDR
A fundamental problem with provenance-based approaches against attackers that auto-generate fake news is identified: fake and legitimate texts can originate from nearly identical sources. Expand
Automatic Detection of Machine Generated Text: A Critical Survey
TLDR
An in-depth error analysis of the state-of-the-art detector is conducted and research directions are discussed to guide future work in this exciting area. Expand
Reverse Engineering Configurations of Neural Text Generation Models
TLDR
This work conducts an extensive suite of diagnostic tests to observe whether modeling choices leave detectable artifacts in the text they generate, and finds that such artifacts are present and that different modeling choices can be inferred by looking at generated text alone. Expand
Fully Automatic Journalism: We Need to Talk About Nonfake News Generation
TLDR
The first fully automatic news generators are going into production without much media furore or awareness among readers, driven by very different, fully controllable and as yet undetectable, text generation technologies. Expand
Fact-Enhanced Synthetic News Generation
TLDR
A new generation method FactGen is developed to generate high-quality news content that retrieves external facts to enrich the output and reconstructs the input claim from the generated content to improve the consistency among the input and the output. Expand
Fake news detection using discourse segment structure analysis
TLDR
The primary aim of this paper is to review existing methodologies, to propose and implement a method for automated deception detection, which uses deep learning in discourse-level structure analysis to formulate the structure that differentiates fake and real news. Expand
How Effectively Can Machines Defend Against Machine-Generated Fake News? An Empirical Study
TLDR
Empirically study the effectiveness of machine-generated fake news detectors by understanding the model’s sensitivity to different synthetic perturbations during test time and believe the code could be a useful diagnostic tool for evaluating models aimed at fighting machine- generated fake news. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 59 REFERENCES
"Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection
TLDR
This paper presents liar: a new, publicly available dataset for fake news detection, and designs a novel, hybrid convolutional neural network to integrate meta-data with text to improve a text-only deep learning model. Expand
Language GANs Falling Short
TLDR
The impact of exposure bias on sample quality is less severe than previously thought, and temperature tuning provides a better quality / diversity trade-off than adversarial training while being easier to train, easier to cross-validate, and less computationally expensive. Expand
SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
TLDR
This paper introduces the task of grounded commonsense inference, unifying natural language inference and commonsense reasoning, and proposes Adversarial Filtering (AF), a novel procedure that constructs a de-biased dataset by iteratively training an ensemble of stylistic classifiers, and using them to filter the data. Expand
The Curious Case of Neural Text Degeneration
TLDR
By sampling text from the dynamic nucleus of the probability distribution, which allows for diversity while effectively truncating the less reliable tail of the distribution, the resulting text better demonstrates the quality of human text, yielding enhanced diversity without sacrificing fluency and coherence. Expand
HellaSwag: Can a Machine Really Finish Your Sentence?
TLDR
The construction of HellaSwag, a new challenge dataset, and its resulting difficulty, sheds light on the inner workings of deep pretrained models, and suggests a new path forward for NLP research, in which benchmarks co-evolve with the evolving state-of-the-art in an adversarial way, so as to present ever-harder challenges. Expand
Unifying Human and Statistical Evaluation for Natural Language Generation
TLDR
This paper proposes a unified framework which evaluates both diversity and quality, based on the optimal error rate of predicting whether a sentence is human- or machine-generated, called HUSE, which is efficiently estimated by combining human and statistical evaluation. Expand
Automatic Detection of Fake News
TLDR
This paper introduces two novel datasets for the task of fake news detection, covering seven different news domains, and conducts a set of learning experiments to build accurate fake news detectors that can achieve accuracies of up to 76%. Expand
Toward Controlled Generation of Text
TLDR
A new neural generative model is proposed which combines variational auto-encoders and holistic attribute discriminators for effective imposition of semantic structures inGeneric generation and manipulation of text. Expand
FEVER: a large-scale dataset for Fact Extraction and VERification
TLDR
This paper introduces a new publicly available dataset for verification against textual sources, FEVER, which consists of 185,445 claims generated by altering sentences extracted from Wikipedia and subsequently verified without knowledge of the sentence they were derived from. Expand
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
TLDR
A benchmark of nine diverse NLU tasks, an auxiliary dataset for probing models for understanding of specific linguistic phenomena, and an online platform for evaluating and comparing models, which favors models that can represent linguistic knowledge in a way that facilitates sample-efficient learning and effective knowledge-transfer across tasks. Expand
...
1
2
3
4
5
...