Browse State-of-the-Art › Adversarial Text
Adversarial Text
51 papers with code · 0 benchmarks · 2 datasets archive 2025-07-28
Adversarial Text refers to a specialised text sequence that is designed specifically to influence the prediction of a language model. Generally, Adversarial Text attack are carried out on Large Language Models (LLMs). Research on understanding different adversarial approaches can help us build effective defense mechanisms to detect malicious text input and build robust language models.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
2 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 114 · with a code link: 51 · where Syntology ran a sample: 16 (13 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (16 of 114 tagged: 13 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 114, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
17 May 2016 39 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified (of 19 harvested samples) · 6 pointer-only (licence)Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal.
-
27 Jul 2019 7 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models.
-
28 Nov 2023 3 repositories listedThis paper introduces RETSim (Resilient and Efficient Text Similarity), a lightweight, multilingual deep learning model trained to produce robust metric embeddings for near-duplicate text retrieval, clustering, and…
-
29 Dec 2020 3 repositories listed Syntology official (archive's flag): 4 ran · 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 6 pointer-only (licence)Our proposed attack strategy leverages population-based optimization algorithm to craft plausible and semantically similar adversarial examples by observing only the top label predicted by the target model.
-
22 Dec 2019 3 repositories listedIn particular, we propose a tree-based autoencoder to embed the discrete text data into a continuous representation space, upon which we optimize the adversarial perturbation.
-
23 Aug 2021 2 repositories listedIn this paper, we propose a Bigram and Unigram based adaptive Semantic Preservation Optimization (BU-SPO) method to examine the vulnerability of deep models.
-
9 Sep 2020 2 repositories listedWe study the behavior of several black-box search algorithms used for generating adversarial examples for natural language processing (NLP) tasks.
-
5 Jun 2020 2 repositories listed Syntology 10 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 12 harvested samples) · 12 pointer-only (licence)Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest.
-
29 Apr 2020 2 repositories listedTextAttack also includes data augmentation and adversarial training modules for using components of adversarial attacks to improve model accuracy and robustness.
-
4 Apr 2020 2 repositories listedModern text classification models are susceptible to adversarial examples, perturbed versions of the original text indiscernible by humans which get misclassified by the model.
-
13 Jan 2018 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)Although various techniques have been proposed to generate adversarial samples for white-box attacks on text, little attention has been paid to black-box attacks, which are more realistic scenarios.
-
8 Apr 2025 1 repository listedThe integration of large language models (LLMs) into information retrieval systems introduces new attack surfaces, particularly for adversarial ranking manipulations.
-
2 Apr 2025 1 repository listedThis paper aims to scrutinize the inherent vulnerabilities of such models in Twitter sentiment analysis.
-
10 Feb 2025 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)To understand the complexity of sequence classification tasks, Hahn et al. (2021) proposed sensitivity as the number of disjoint subsets of the input sequence that can each be individually changed to change the output.
-
20 Dec 2024 1 repository listedAdversarial attacks seek to manipulate the ranking of documents, with the intention of exposing users to targeted content.
-
13 Dec 2024 1 repository listedOften these attacks remove one token at a time to find the ideal one to change, requiring n queries (the length of the text) right away.
-
3 Dec 2024 1 repository listedTo address this issue, we propose a novel Tibetan adversarial text generation method called TSCheater, which considers the characteristic of Tibetan encoding and the feature that visually similar syllables have similar…
-
19 Nov 2024 1 repository listedIn this paper, we propose a new type of adversarial attack against NMT models.
-
28 Oct 2024 1 repository listedRecent advances in diffusion models have significantly enhanced the quality of image synthesis, yet they have also introduced serious safety concerns, particularly the generation of Not Safe for Work (NSFW) content.
-
3 Oct 2024 1 repository listedWe design, implement, and evaluate adversarial decoding, a new, generic text generation technique that produces readable documents for different adversarial objectives.
-
8 Sep 2024 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 4 unverified (of 4 harvested samples) · 4 pointer-only (licence)However, existing studies on adversarial attacks are insufficient in both attacking ability and human imperceptibility due to their sole focus on the scope of language.
-
1 Aug 2024 1 repository listedText-aware recommender systems incorporate rich textual features, such as titles and descriptions, to generate item recommendations for users.
-
18 Jun 2024 1 repository listed Syntology official (archive's flag): 16 ran · 16 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified (of 21 harvested samples) · 1 pointer-only (licence)To bridge this gap, we manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena, a real environment for web agents.
-
28 May 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)Subsequently, an adversarial text suffix is integrated and co-optimized with the adversarial image prefix to maximize the probability of eliciting affirmative responses to various harmful instructions.
-
30 Apr 2024 1 repository listed Syntology official (archive's flag): 18 ran · 18 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 12 where Syntology's instrument failed) · 4 unverified (of 22 harvested samples) · 5 pointer-only (licence)To this end, this work presents the first comprehensive study on improving the adversarial robustness of VLMs against attacks targeting image, text, and multimodal inputs.
-
21 Mar 2024 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples) · 2 pointer-only (licence)The vulnerability of deep neural networks to imperceptible adversarial perturbations has attracted widespread attention.
-
19 Mar 2024 1 repository listedVision-language pre-training (VLP) models exhibit remarkable capabilities in comprehending both images and text, yet they remain susceptible to multimodal adversarial examples (AEs).
-
18 Feb 2024 1 repository listedFirst, empirical analyses show that (a) extracted features can be used with a lightweight classifier such as Random Forest to predict the attack success rate effectively, and (b) features with the most influence on the…
-
5 Feb 2024 1 repository listedTo evaluate the grammatical and semantic similarities of the newly produced adversarial examples using our synonym BERT-based attack, we invite four human evaluators to assess and compare the produced adversarial…
-
29 Oct 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples) · 1 pointer-only (licence)In this paper, we systematically evaluate the robustness of multi-exit language models against adversarial slowdown.
-
2 Jun 2023 1 repository listed
-
8 May 2023 1 repository listed
-
29 Mar 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
1 Mar 2023 1 repository listed
-
18 Feb 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 7 harvested samples)
-
10 Feb 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
17 Nov 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 6 harvested samples)
-
23 Oct 2022 1 repository listed
-
3 May 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
10 Apr 2022 1 repository listed
-
2 Mar 2022 1 repository listed
-
12 Oct 2021 1 repository listed
-
12 May 2021 1 repository listed
-
14 Jan 2021 1 repository listed
-
3 Sep 2020 1 repository listed
-
21 Aug 2019 1 repository listed
-
13 Dec 2018 1 repository listed
-
1 Dec 2018 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
17 Sep 2018 1 repository listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
14 Dec 2017 1 repository listed
-
Adversarial Text Generation with Dynamic Contextual Perturbation10 Jun 2025 0 repositories listed
-
A Grey-box Text Attack Framework using Explainable AI11 Mar 2025 0 repositories listed
-
Continuous Adversarial Text Representation Learning for Affective Recognition28 Feb 2025 0 repositories listed
-
Hierarchical Lexical Manifold Projection in Large Language Models: A Novel Mechanism for Multi-Scale Semantic Representation8 Feb 2025 0 repositories listed
-
Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization15 Dec 2024 0 repositories listed
-
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization8 Dec 2024 0 repositories listed
-
SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments28 Nov 2024 0 repositories listed
-
IAE: Irony-based Adversarial Examples for Sentiment Analysis Systems12 Nov 2024 0 repositories listed
-
Target-driven Attack for Large Language Models9 Nov 2024 0 repositories listed
-
Graded Suspiciousness of Adversarial Texts to Human6 Oct 2024 0 repositories listed
-
OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation4 Sep 2024 0 repositories listed
-
Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion1 Aug 2024 0 repositories listed
-
Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent29 Jul 2024 0 repositories listed
-
Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?11 Jun 2024 0 repositories listed
-
Phantom: General Trigger Attacks on Retrieval Augmented Language Generation30 May 2024 0 repositories listed
-
R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model25 May 2024 0 repositories listed
-
Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods8 Apr 2024 0 repositories listed
-
Goal-guided Generative Prompt Injection Attack on Large Language Models6 Apr 2024 0 repositories listed
-
Adversarial Text Purification: A Large Language Model Approach for Defense5 Feb 2024 0 repositories listed
-
Adversarial Text to Continuous Image Generation1 Jan 2024 0 repositories listed
-
Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?9 Jun 2023 0 repositories listed
-
How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks24 May 2023 0 repositories listed
-
Iterative Adversarial Attack on Image-guided Story Ending Generation16 May 2023 0 repositories listed
-
Towards Imperceptible Document Manipulations against Neural Ranking Models3 May 2023 0 repositories listed
-
Improved Training of Mixture-of-Experts Language GANs23 Feb 2023 0 repositories listed
-
TextDefense: Adversarial Text Detection based on Word Importance Entropy12 Feb 2023 0 repositories listed
-
A survey on text generation using generative adversarial networks20 Dec 2022 0 repositories listed
-
PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks1 Oct 2022 0 repositories listed
-
Adversarial Text Normalization8 Jun 2022 0 repositories listed
-
Detecting Word-Level Adversarial Text Attacks via SHapley Additive exPlanations1 May 2022 0 repositories listed
-
“That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks1 May 2022 0 repositories listed
-
Data-Driven Mitigation of Adversarial Text Perturbation19 Feb 2022 0 repositories listed
-
Identifying Adversarial Attacks on Text Classifiers21 Jan 2022 0 repositories listed
-
SemAttack: Natural Textual Attacks via Different Semantic Spaces16 Jan 2022 0 repositories listed
-
Repairing Adversarial Texts through Perturbation29 Dec 2021 0 repositories listed
-
"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks16 Nov 2021 0 repositories listed
-
Don’t Search for a Search Method — Simple Heuristics Suffice for Adversarial Text Attacks1 Nov 2021 0 repositories listed
-
Improving Adversarial Text Generation with n-Gram Matching1 Nov 2021 0 repositories listed
-
What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations1 Nov 2021 0 repositories listed
-
Generating Watermarked Adversarial Texts25 Oct 2021 0 repositories listed
-
Adversarial Training: A simple and efficient technique to Improving NLP Robustness29 Sep 2021 0 repositories listed
-
Don't Search for a Search Method -- Simple Heuristics Suffice for Adversarial Text Attacks16 Sep 2021 0 repositories listed
-
Reinforce Attack: Adversarial Attack against BERT with Reinforcement Learning17 Aug 2021 0 repositories listed
-
DISCO : efficient unsupervised decoding for discrete natural language problems via convex relaxation7 Jul 2021 0 repositories listed
-
Detecting Adversarial Text Attacks via SHapley Additive exPlanations16 May 2021 0 repositories listed
-
"TL;DR:" Out-of-Context Adversarial Text Summarization and Hashtag Recommendation1 Apr 2021 0 repositories listed
-
Adversarial Text-to-Image Synthesis: A Review25 Jan 2021 0 repositories listed
-
From Unsupervised Machine Translation To Adversarial Text Generation10 Nov 2020 0 repositories listed
-
Adversarial Text Generation via Sequence Contrast Discrimination1 Nov 2020 0 repositories listed
Syntology lines on 18 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections