This release includes the following updates
- Add RewriteRollbackStrategy, SAPStrategy.
- Redesign defense strategy API.
- Add AdvTrainStrategy, SEMStrategy, SAPDStrategy
This release includes the following updates
- Add
dynamic_len
seed option to ASRS, so the paraphrase can have different length. - Fix bug in
asrs_utils_lm
This release includes the following updates
- Rename BertSamplingStrategy model as ASRSStrategy.
- Update ASRS to use Cross Encoder as default similarity metric.
- Add timeout feature to TextAttackStrategy.
- Update benchmark results.
- Add paper reference.
This release is an emergency bug fix.
- Fix the bug in DatasetForBert introduced by the previous update.
This release includes the following updates
- Improve the doc string and documentation for adversarial training.
- Add experimental code about non-autoregressive paraphrase strategy.
This release adds experimental code to adversarial training.
- Add a default adversarial tuning strategy.
- Add API in classifiers to support adversarial tuning.
- Add args in benchmark for adversarial tuning.
This release fixes bugs and adds unit tests.
- Add Sentence BERT metric and corresponding unit test.
- Fix the bug of the colab demo.
This release improves documentation and unit tests.
- Add integrity test for IdentityStrategy, TextAttackStrategy, and BertSamplingStrategy.
- For IdentityStrategy and TextAttackStrategy, accuracy is verified.
- Improve documentation, split data format from benchmark.
This release updates the structure of the project and improve documentation.
- Metric module is redesigned to have a consistant API. (Issue #12)
- More unit tests are added. Slow unit tests are skipped in CI. (Issue #11)
- Benchmark table is updated. (Issue #10)
- Better support to
TextAttack
. Users can choose any implemented attacking method inTextAttack
using theta_recipe
arg. (Issue #9)
This release includes the following updates:
- Add a benchmark class. Users can integrate fibber benchmark to other projects. The class supports customized datasets, target classifier and attacking method.
- Migrate from Travis CI to Github Action.
- Move adversarial-attack-related aggragation functions from benchmark module to metric module.
This minor release add pretrained classifiers and downloadable resources on a demo dataset, and a demo Colab.
This minor release removes the dependency on textattack
because it produces dependency conflicts.
Users can install it manually to use attacking strategies in textattack
.
This release is a major update to Fibber library. Advanced paraphrase algorithms are included.
- Add two strategies: TextFoolerStrategy and BertSamplingStrategy.
- Improve the benchmarking framework: add more metrics specifically designed for adversarial attack.
- Datasets: add a variation of AG's news dataset,
ag_no_title
. - Bug fix and improvements.
This is the first release of Fibber library. This release contains:
- Datasets: fibber contains 6 built-in datasets.
- Metrics: fibber contains 6 metrics to evaluate the quality of paraphrased sentences. All metrics have a unified interface.
- Benchmark framework: the benchmark framework and easily evaluate the phraphrase strategies on built-in datasets and metrics.
- Strategies: this release contains 2 basic strategies, the identity strategy and random strategy.
- A unified Fibber interface: users can easily use fibber by creating a Fibber object.