falcondai / lm-steganography
Steganographic text via language models
☆20Updated last year
Related projects ⓘ
Alternatives and complementary repositories for lm-steganography
- Code for ACL'20 paper "It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations"☆19Updated last year
- Probing task; contextual embeddings -> textual definitions (EMNLP19)☆11Updated 3 years ago
- ☆30Updated 2 years ago
- An attempt to use a Generative Adversarial Network (GAN) for natural language generation.☆16Updated 6 years ago
- Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding in EMNLP 2020☆18Updated 4 years ago
- EMNLP BlackBox NLP 2020: Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples☆23Updated 4 years ago
- ☆62Updated 2 years ago
- Code for "Imitation Attacks and Defenses for Black-box Machine Translations Systems"☆36Updated 4 years ago
- ☆21Updated 3 years ago
- [EMNLP 2020] "T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack" by Boxin Wang, Hengzhi Pei, Boyuan Pan, Q…☆26Updated 3 years ago
- A Cross-Domain Transferable Neural Coherence Model https://arxiv.org/abs/1905.11912☆24Updated 4 years ago
- ☆26Updated 5 years ago
- Implementation of "Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model"☆24Updated 3 years ago
- ☆26Updated last year
- ☆10Updated 6 years ago
- Code for our ACL '20 paper "Representation Engineering with Natural Language Explanations"☆29Updated 4 years ago
- SUM-QE, a BERT-based Summary Quality Estimation Model☆21Updated last year
- Scripts and noise data for Belinkov & Bisk 2018☆29Updated 6 years ago
- Unsupervised text segmentation based on Latent Dirichlet Allocation and Topic Tiling☆24Updated 8 years ago
- Concealed Data Poisoning Attacks on NLP Models☆20Updated last year
- Adversarial examples for Seq2Seq model in NLP☆39Updated 6 years ago
- ☆16Updated 4 years ago
- Tool for Evaluating Adversarial Perturbations on Text☆62Updated 2 years ago
- CodeBase for Paper: "Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers", / Interactive Demo @☆73Updated last year
- STEGASURAS: STEGanography via Arithmetic coding and Strong neURAl modelS☆185Updated 3 months ago
- Code for bidirectional sequence generation (BiSon) for generating from BERT pre-trained models.☆52Updated 4 years ago
- Code for the paper Learning Domain-specific Representations for Multi-Domain Sentiment Classification☆30Updated 4 years ago
- Natural Language Generation by Hierarchical Decoding with Linguistic Patterns (NAACL-HLT 2018), Investigating Linguistic Pattern Ordering…☆33Updated 6 years ago
- Source code for Text Infilling, implemented with Texar.☆26Updated 5 years ago
- TextGraphs-13 Shared Task on Multi-Hop Inference Explanation Regeneration☆44Updated 4 years ago
- ☆21Updated 3 months ago