The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
All You Need is "Love": Evading Hate Speech Detection
Open accessAbstract
With the spread of social networks and their unfortunate use for hate speech, automatic detection of the latter has become a pressing problem. In this paper, we reproduce seven state-of-the-art hate speech detection models from prior work, and show that they perform well only when tested on the same type of data they were trained on. Based on these results, we argue that for successful hate speech detection, model architecture is less important than the type of data and labeling criteria. We further show that all proposed detection techniques are brittle against adversaries who can (automatically) insert typos, change word boundaries or add innocuous words to the original hate speech. A combination of these methods is also effective against Google Perspective - a cutting-edge solution from industry. Our experiments demonstrate that adversarial training does not completely mitigate the attacks, and using character-level features makes the models systematically more attack-resistant than using word-level features.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568
False Information on Web and Social Media: A Survey
Kumar, S., & Shah, N. (2018) · arXiv · doi:10.48550/arxiv.1804.08559 · Cited by 289 · cited 1×
“While the ability of ordinary people to reach thousands of others instantenously undoubtedly has positive effects, downsides like polarization via echo chambers [13] have become apparent.”
BackgroundWhat is hate speech? Part 1: The Myth of Hate
Brown, A. (2017) · Law and Philosophy · doi:10.1007/s10982-017-9297-1 · Cited by 246
Cited by
HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
Mathew, B., Saha, P., Yimam, S. M., Biemann, C., Goyal, P., & Mukherjee, A. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i17.17745 · Cited by 513
Developing an online hate classifier for multiple social media platforms
Salminen, J., Hopf, M., Chowdhury, S. A., Jung, S.-G., Almerekhi, H., & Jansen, B. J. (2020) · Human-centric Computing and Information Sciences · doi:10.1186/s13673-019-0205-6 · Cited by 286
Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection
Vidgen, B., Thrush, T., Waseem, Z., & Kiela, D. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.132 · Cited by 174
A New Generation of Perspective API: Efficient Multilingual Character-level Transformers
Lees, A., Tran, V. Q., Tay, Y., Sorensen, J., Gupta, J., Metzler, D., & Vasserman, L. (2022) · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3534678.3539147 · Cited by 155
Metadata
- Authors
- Gröndahl, T., Pajola, L., Juuti, M., Conti, M., & Asokan, N.
- Venue
- Proceedings of the 11th ACM Workshop on Artificial Intelligence and Security
- Publisher
- ACM
- Published
- 2018-01-15
- Pages
- 2-12
- OpenAlex
- W2889016530
- Cited by
- 203
- References
- 3
- FWCI
- 10.09
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.