Pith. sign in

REVIEW 13 cited by

TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2005.05909 v4 pith:DPQFABCH submitted 2020-04-29 cs.CL cs.AIcs.LG

John X. Morris , Eli Lifland , Jin Yong Yoo , Jake Grigsby , Di Jin , Yanjun Qi This is my paper
classification cs.CLcs.AIcs.LG
keywords adversarialattackstextattackaugmentationdatatrainingcodecomponents
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

While there has been substantial research using adversarial attacks to analyze NLP models, each attack is implemented in its own code repository. It remains challenging to develop NLP attacks and utilize them to improve model performance. This paper introduces TextAttack, a Python framework for adversarial attacks, data augmentation, and adversarial training in NLP. TextAttack builds attacks from four components: a goal function, a set of constraints, a transformation, and a search method. TextAttack's modular design enables researchers to easily construct attacks from combinations of novel and existing components. TextAttack provides implementations of 16 adversarial attacks from the literature and supports a variety of models and datasets, including BERT and other transformers, and all GLUE tasks. TextAttack also includes data augmentation and adversarial training modules for using components of adversarial attacks to improve model accuracy and robustness. TextAttack is democratizing NLP: anyone can try data augmentation and adversarial training on any model or dataset, with just a few lines of code. Code and tutorials are available at https://github.com/QData/TextAttack.

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research

    cs.LG 2025-09 conditional novelty 6.0 of 10

    A modular fault injection framework for transformers, enabling controlled study of how weight, activation, and attention faults degrade LLM performance.

  2. Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Diffusion Tree Sampling is a Monte Carlo tree search over denoising trajectories that propagates terminal rewards backward to sample from reward-aligned distributions, showing up to 10x compute savings on tested benchmarks.

  3. A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Blind text-only likelihood models match or exceed CLIP on many compositionality benchmarks because positives and negatives differ systematically in length, plausibility, or image style.

  4. Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A new taxonomy and dataset of 8 types of perturbed toxic Chinese show nine top LLMs often miss these obfuscated insults, and small-sample ICL or fine-tuning causes overcorrection.

  5. SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language Models

    cs.CL 2025-05 conditional novelty 6.0 of 10

    SocialMaze is a six-task benchmark that claims to evaluate LLM social reasoning along deep reasoning, dynamic interaction, and information uncertainty dimensions.

  6. Evaluation of Adversarial Robustness in Arabic Language Models

    cs.CL 2026-07 conditional novelty 5.0 of 10

    Arabic BERT-family sentiment models lose up to 92% accuracy under diacritics and 58% under conjunction attacks; paraphrase attacks cut accuracy by 76% on average, and adversarial training only partially helps.

  7. SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds

    cs.LG 2025-08 conditional novelty 5.0 of 10

    SALMAN ranks each text sample's fragility via the distortion between input and output embedding distances and uses the ranking to improve attack success rates and fine-tuning robustness.

  8. Practical, Generalizable and Robust Backdoor Attacks on Text-to-Image Diffusion Models

    cs.CR 2025-08 unverdicted novelty 5.0 of 10

    The abstract claims that 10 poisoned samples can backdoor multiple text-to-image models with over 90% attack success and resistance to defenses, but the supplied body is a different paper.

  9. ROBAD: Robust Adversary-aware Local-Global Attended Bad Actor Detection Sequential Model

    cs.LG 2025-07 conditional novelty 5.0 of 10

    ROBAD combines a transformer encoder-decoder with contrastive adversarial training to detect bad actors from user post sequences, achieving higher F1 and lower F1 drop under next-post attacks than baselines.

  10. Investigating the Robustness of Retrieval-Augmented Generation at the Query Level

    cs.CL 2025-07 conditional novelty 5.0 of 10

    Retrieval-augmented generation performance drops noticeably under minor query perturbations, with end-to-end results often tracking retriever behavior.

  11. Unveiling Unicode's Unseen Underpinnings in Undermining Authorship Attribution

    cs.CR 2025-08 unverdicted novelty 4.0 of 10

    The paper proposes integrating Unicode steganography into adversarial stylometry to undermine authorship attribution.

  12. PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training

    cs.CR 2025-07 reject novelty 3.0 of 10

    A PRM-free alignment pipeline combining genetic algorithm red teaming and multi-objective adversarial training is claimed to beat PRM-based methods at 61% lower cost, but the experiments are unverifiable.

  13. The Societal Impact of Foundation Models: Advancing Evidence-based AI Policy

    cs.AI 2025-06 conditional novelty 2.0 of 10

    A dissertation that synthesizes prior work on foundation models into a three-part framework: conceptual framing, empirical measurement (HELM, FMTI), and evidence-based AI policy.

Pith tools