v1.2.1

Changes:

• Rename repository from AI-SDC to SACRO-ML (#298)
• Rename package from aisdc sacroml (#299)

v.1.2.0

Changes:

• Add support for scikit-learn MLPClassifier (#276)
• Use default XGBoost params if not defined in structural attacks (#277)
• Clean up documentation (#282)
• Clean up repository and update packaging (#283)
• Format docstrings (#286)
• Refactor (#284, #285, #287)
• Add CLI and tools for generating configs; significant refactor (#291)
• Add different implementation modes for online and offline LiRA (#281)

v.1.1.3

Changes:

• Add built-in support for additional datasets (#257)
• Remove references to final score in outputs (#259)
• Update package dependencies: remove support for Python 3.8; add support for Python 3.11 (#262)
• Fix code coverage reporting (#265)
• Remove useless pylint suppression pragmas (#269)
• Fix axis labels in report ROC curve plot (#270)

v.1.1.2

Changes:

• Fix a bug related to the rules.json path when running from package (#247)
• Update user stories (#247)

v.1.1.1

Changes:

• Update notebook example paths (#237)
• Fix AdaBoostClassifier structural attack (#242)
• Move experiments module and configs to separate repository (#229)

v.1.1.0

Changes:

• Add automatic formatting of docstrings (#210)
• Update user stories (#217)
• Add module to run experiments with attacks and gather data (#224)
• Fix bug in report.py: error removing a file that does not exist (#227)
• Add structural attack for traditional and other risk measures (#232)
• Fix package installation for Python 3.8, 3.9, 3.10 (#234)

v.1.0.6

Changes:

• Update package dependencies (#187)
• Fix bug when n_dummy_reps=0 in worst case attack (#191)
• Add ability to save target model and data to target.json (#171, #175, #176, #177)
• Add safemodel SDC results to target.json and attack_results.json (#180)
• Add generalisation error to target.json (#183)
• Refactor attack argument handling (#174)
• Append attack outputs to a single results file (#173)
• Attack outputs written to specified folder (#208)
• Add ability to run membership inference attacks from the command line using config and target files (#182)
• Add ability to run attribute inference attacks from the command line using config and target files (#188)
• Add ability to run multiple attacks from a config file (#200)
• Add user story examples (#194)
• Improve attack formatter summary generation (#179)
• Attack formatter moves files generated for release into subfolders (#197)
• Fix a minor bug in the attack formatter (#204)
• Improve tests (#196, #199)

v.1.0.5

Changes since v.1.0.4:

• Fix a bug calculating the number of data samples in the Data class (#105)
• Add a fail-fast mechanism for the worst case attack that enables the number of attack repetitions to terminate early based on a given metric and comparison operator (#105)
• Change the logging message when attack repetitions are run to 1-10 instead of 0-9 (#105)
• Add the ability to specify the number of worst case attack dummy repetitions on the command line (#105)
• Add LIRA fail-fast mechanism (#118)
• Add the ability to load LIRA attack parameters from a config file (#118)
• Add the ability to load worst case attack parameters from a config file (#119)
• Standardise the MIA attack output (#120)
• Prohibit the use of white space in report file names (#154)
• Improve the safemodel request release test (#160)
• Refactor LIRA attack tests (#151)
• Fix setting the number of LIRA shadow models from a config file (#165)
• Fix OS system calls relying on calling "python" (#162)
• Fix invalid command line argument in worst case attack example (#164)
• Add current output JSON format documentation (#168)
• Add current attack config format documentation (#168)

v.1.0.4

Changes since v.1.0.3:

• Fixed SafeRandomForestClassifier "base estimator changed" error .

v.1.0.3

Changes since v.1.0.2:

• Refactored metrics.
• Fixed a bug making a report when dummy reps is 0.
• Fixed safemodel JSON output.
• Added a module to produce recommendations from attack JSON output.
• Disabled non-default report logs.
• Fixed a minor bug in worst case example.