joey1993 / bert-defender

Related projects: ⓘ

• lushleaf / Structure-free-certified-NLP
  SAFER: A Structure-free Approach For cErtified Robustness to Adversarial Word Substitutions (ACL 2020)
  ☆27Updated 3 years ago
• JHL-HUST / PWWS
  Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency
  ☆66Updated last year
• robinjia / certified-word-sub
  Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)
  ☆39Updated 4 years ago
• Hsuan-Tung / universal_attack_natural_trigger
  Natural Universal Trigger Search (NUTS)
  ☆21Updated 3 years ago
• thunlp / NeuBA
  ☆22Updated 3 years ago
• thunlp / ONION
  Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"
  ☆28Updated 2 years ago
• JHL-HUST / FGPM
  Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text Attacks
  ☆23Updated 3 years ago
• RishabhMaheshwary / hard-label-attack
  Natural Language Attacks in a Hard Label Black Box Setting.
  ☆40Updated 3 years ago
• AnyiRao / WordAdver
  Code for ACL2018 HotFlip: White-Box Adversarial Examples for Text Classification, Word-level Adversarial Examples
  ☆32Updated 5 years ago
• dugu9sword / dne
  ACL 2021 - Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble
  ☆15Updated last year
• zjiehang / RanMASK
  For Certified Robustness to Text Adversarial Attacks by Randomized [MASK]
  ☆15Updated 2 years ago
• csong27 / collision-bert
  ☆28Updated 3 years ago
• RockyLzy / TextDefender
  codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"
  ☆30Updated 10 months ago
• cmhcbb / Seq2Sick
  Adversarial examples for Seq2Seq model in NLP
  ☆39Updated 5 years ago
• cookielee77 / CLARE
  Contextualized Perturbation for Textual Adversarial Attack, NAACL 2021
  ☆41Updated 3 years ago
• AI-secure / T3
  [EMNLP 2020] "T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack" by Boxin Wang, Hengzhi Pei, Boyuan Pan, Q…
  ☆26Updated 2 years ago
• leix28 / prompt-universal-vulnerability
  Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022
  ☆26Updated 2 years ago
• thunlp / SememePSO-Attack
  Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial Optimization"
  ☆86Updated 3 years ago
• thunlp / StyleAttack
  Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"
  ☆41Updated last year
• lancopku / Embedding-Poisoning
  Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…
  ☆34Updated 3 years ago
• lancopku / SOS
  Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)
  ☆21Updated 2 years ago
• alvinchangw / CARA_EMNLP2020
  Implementation for Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder (EMNLP-Findings 2020)
  ☆15Updated 3 years ago
• ShannonAI / backdoor_nlg
  ☆13Updated 3 years ago
• cecilialeiqi / adversarial_text
  to add
  ☆20Updated 4 years ago
• lancopku / RAP
  Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)
  ☆20Updated 2 years ago
• RishabhMaheshwary / query-attack
  A Query Efficient Natural Language Attack in a Black Box Setting
  ☆16Updated 2 years ago
• LilyNLP / ADFAR
  ☆9Updated 3 years ago
• QData / TextAttack-A2T
  A2T: Towards Improving Adversarial Training of NLP Models (EMNLP 2021 Findings)
  ☆23Updated 3 years ago
• neulab / RIPPLe
  Code for the paper "Weight Poisoning Attacks on Pre-trained Models" (ACL 2020)
  ☆137Updated 2 years ago
• thunlp / HiddenKiller
  Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"
  ☆37Updated 2 years ago