CoChat
Sign Up
Cited by 94Adversarial Robustness in Machine LearningTopic ModelingNatural Language Processing Techniques

Adversarial attack and defense technologies in natural language processing: A survey

Qiu, Shilin, Liu, Qihe, Zhou, Shijie, Huang, Wen·2022·Neurocomputing
DOI 10.1016/j.neucom.2022.04.020
Open this paper in CoChat — free account

Integrity signals

Registry

Crossref · 10.1016/j.neucom.2022.04.020

Cites

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • LLMs generalize better than fine-tuned models in downstream tasks facing out-of-distribution data, such as adversarial examples and domain shifts.

    “(1) LLMs generalize better than fine-tuned models in downstream tasks facing out-ofdistribution data, such as adversarial examples and domain shifts.Evidenced by the comparison-based empirical results in related literature like References [38,95,117], as well as the generalization improvement gained through alignment techniques like Reinforcement Learning from Human Feedback (RLHF) [89].”

    From Harnessing the power of llms in practice: a survey on chatGPT and beyond (2024) · cites this paper as [95]

The citation lists haven’t been fetched yet

References 161 · Cited by 94

Authors
Qiu, S., Liu, Q., Zhou, S., & Huang, W.
Affiliations
  • University of Electronic Science and Technology of China (CN)
  • Huawei Technologies (China) (CN)
Corresponding author
Qiu, Shilin
ORCID
Venue
Neurocomputing
Publisher
Elsevier BV
Published
2022-07
Volume
492
Pages
278-307
ISSN
0925-2312 (ISSN-L)
DOI
10.1016/j.neucom.2022.04.020
OpenAlex
W4224215750
Cited by
94
References
161
Citations by year
2026: 23 · 2025: 23 · 2024: 24 · 2023: 22 · 2022: 2
FWCI
5.84
Type
journal article
Language
en
Open access
closed
Licence
Locations
Neurocomputing (publishedVersion)
Funders
Sichuan Province Science and Technology Support Program (2019YFG0399, 2020YFG0472, 2020YFG0031)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
Keywords
adversarial attacks, adversarial defense, natural language processing, semantic granularity, adversarial datasets, passive defense, active defense

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