Pith. sign in

REVIEW 4 cited by

BERT-ATTACK: Adversarial Attack Against BERT Using BERT

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 2004.09984 v3 pith:ACTIHA2F submitted 2020-04-21 cs.CL

Linyang Li , Ruotian Ma , Qipeng Guo , Xiangyang Xue , Xipeng Qiu This is my paper
classification cs.CL
keywords adversarialbertmodelsattackbert-attacksampleschallengingdata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Adversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based methods. Current successful attack methods for texts usually adopt heuristic replacement strategies on the character or word level, which remains challenging to find the optimal solution in the massive space of possible combinations of replacements while preserving semantic consistency and language fluency. In this paper, we propose \textbf{BERT-Attack}, a high-quality and effective method to generate adversarial samples using pre-trained masked language models exemplified by BERT. We turn BERT against its fine-tuned models and other deep neural models in downstream tasks so that we can successfully mislead the target models to predict incorrectly. Our method outperforms state-of-the-art attack strategies in both success rate and perturb percentage, while the generated adversarial samples are fluent and semantically preserved. Also, the cost of calculation is low, thus possible for large-scale generations. The code is available at https://github.com/LinyangLee/BERT-Attack.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. 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.

  2. Evaluating LLMs Robustness in Less Resourced Languages with Proxy Models

    cs.CL 2025-06 conditional novelty 5.0 of 10

    Important words chosen by a small proxy model, when perturbed with typos or spacing errors, push Bielik, Mistral-7B, and Llama-3.1-8B to wrong answers on Polish classification tasks more often than random edits.

  3. Coordinated Robustness Evaluation Framework for Vision-Language Models

    cs.CV 2025-06 conditional novelty 4.0 of 10

    A coordinated image-plus-text attack built on a surrogate multimodal encoder achieves 80-94% attack success against ViLT, BLIP, and GIT on VQA and visual reasoning, surpassing cited baselines.

  4. 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.

Pith tools