robinjia / certified-word-subView external linksLinks
Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)
☆38Dec 30, 2019Updated 6 years ago
Alternatives and similar repositories for certified-word-sub
Users that are interested in certified-word-sub are comparing it to the libraries listed below
Sorting:
- SAFER: A Structure-free Approach For cErtified Robustness to Adversarial Word Substitutions (ACL 2020)☆31Jan 27, 2021Updated 5 years ago
- [ICLR 2020] Code for paper "Robustness Verification for Transformers"☆27Nov 26, 2024Updated last year
- ☆25May 6, 2021Updated 4 years ago
- ACL 2021 - Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble☆18Jun 12, 2023Updated 2 years ago
- codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"☆31Oct 27, 2023Updated 2 years ago
- codes for paper "learning to discriminate perturbations for blocking adversarial attacks in text classification" in EMNLP19☆15Feb 25, 2020Updated 5 years ago
- ☆10Oct 28, 2020Updated 5 years ago
- Implementation code for the paper "Generating Natural Language Adversarial Examples"☆170Aug 30, 2019Updated 6 years ago
- [EMNLP 2020] "T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack" by Boxin Wang, Hengzhi Pei, Boyuan Pan, Q…☆26Oct 19, 2021Updated 4 years ago
- Code for ACL'20 paper "It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations"☆19May 1, 2025Updated 9 months ago
- Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial Optimization"☆88Apr 11, 2021Updated 4 years ago
- Natural Language Attacks in a Hard Label Black Box Setting.☆50May 26, 2021Updated 4 years ago
- Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency☆72Mar 24, 2023Updated 2 years ago
- ☆10Jun 23, 2018Updated 7 years ago
- "Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers" (NeurIPS 2019, previously called "A Stratified Approach …☆17Nov 16, 2019Updated 6 years ago
- This is the code of our work CISS Certified Robustness Against Natural Language Attacks by Causal Intervention published on ICML 2022☆11Dec 6, 2022Updated 3 years ago
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆32Jul 11, 2022Updated 3 years ago
- Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text Attacks☆24Dec 11, 2020Updated 5 years ago
- ☆14May 7, 2024Updated last year
- EMNLP BlackBox NLP 2020: Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples☆26Oct 11, 2020Updated 5 years ago
- A Model for Natural Language Attack on Text Classification and Inference☆528Dec 8, 2022Updated 3 years ago
- syntactically controlled paraphrase networks☆168Dec 30, 2018Updated 7 years ago
- ☆11Mar 6, 2022Updated 3 years ago
- auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks and General Computational Graphs☆338Feb 3, 2026Updated last week
- ☆64Apr 11, 2022Updated 3 years ago
- A Query Efficient Natural Language Attack in a Black Box Setting☆17Sep 23, 2021Updated 4 years ago
- Code base for the EMNLP 2021 paper, "Multi-granularity Textual Adversarial Attack with Behavior Cloning".☆13Apr 18, 2022Updated 3 years ago
- Code for the paper "MMA Training: Direct Input Space Margin Maximization through Adversarial Training"☆34Apr 1, 2020Updated 5 years ago
- This repo keeps track of popular provable training and verification approaches towards robust neural networks, including leaderboards on …☆98Oct 18, 2022Updated 3 years ago
- Adversarial perturbations on word embeddings of BERT☆13Jan 17, 2021Updated 5 years ago
- Adversarial Training for Natural Language Understanding☆253Sep 6, 2023Updated 2 years ago
- CROWN: A Neural Network Verification Framework for Networks with General Activation Functions☆39Dec 13, 2018Updated 7 years ago
- Create augmentation examples from MultiNLI by subject-object inversion and passivizing.☆17Feb 22, 2021Updated 4 years ago
- Certified defense to adversarial examples using CROWN and IBP. Also includes GPU implementation of CROWN verification algorithm (in PyTor…☆98Jun 7, 2021Updated 4 years ago
- For Certified Robustness to Text Adversarial Attacks by Randomized [MASK]☆17Oct 8, 2024Updated last year
- Contextualized Perturbation for Textual Adversarial Attack, NAACL 2021☆44Jul 23, 2021Updated 4 years ago
- Adversarial examples for Seq2Seq model in NLP☆40Nov 3, 2018Updated 7 years ago
- Code for "Semantically Equivalent Adversarial Rules for Debugging NLP Models"☆87Oct 16, 2018Updated 7 years ago
- Must-read Papers on Textual Adversarial Attack and Defense☆1,575Jun 4, 2025Updated 8 months ago