Skip to content

Tags: RomiconEZ/llamator

Tags

v2.2.0

Toggle v2.2.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Release v2.2.0 (#86)

* Add HarmBench Prompts

* Add Suffix Attack

* Remake Harmful Behavior Attack

---------

Co-authored-by: Shine-afk <belyaevskij.nikita@gmail.com>
Co-authored-by: Timur Nizamov <abc@nizamovtimur.ru>
Co-authored-by: Nikita Ivanov <nikita.ivanov.778@gmail.com>

v2.1.0

Toggle v2.1.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Release v2.1.0 (#80)

* Add Crescendo attack

* Add BON attack

* Add Docker example with Jupyter Notebook and installed LLAMATOR

* Improve attack system prompt for Prompt Leakage

* Other minor improvements and bug fixes

---------

Co-authored-by: Timur Nizamov <abc@nizamovtimur.ru>
Co-authored-by: Nikita Ivanov <nikita.ivanov.778@gmail.com>

v2.0.1

Toggle v2.0.1's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Release v2.0.1 (#67)

* small fix for attacks and add strip parameter for ChatSession

---------

Co-authored-by: Низамов Тимур Дамирович <abc@nizamovtimur.ru>

v2.0.0

Toggle v2.0.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Release v2.0.0 (#64)

What's New:

New Features & Enhancements
- Introduced Multistage Attack: We've added a novel `multistage_depth` parameter to the `start_testing()` fucntion, allowing users to specify the depth of a dialogue during testing, enabling more sophisticated and targeted LLM Red teaming strategies.
- Refactored Sycophancy Attack: The `sycophancy_test` has been renamed to `sycophancy`, transforming it into a multistage attack for increased effectiveness in uncovering model vulnerabilities.
- Enhanced Logical Inconsistencies Attack: The `logical_inconsistencies_test` has been renamed to `logical_inconsistencies` and restructured as a multistage attack to better detect and exploit logical weaknesses within language models.
- New Multistage Harmful Behavior Attack: Introducing `harmful_behaviour_multistage`, a more nuanced version of the original harmful behavior attack, designed for deeper penetration testing.
- Innovative System Prompt Leakage Attack: We've developed a new multistage attack, `system_prompt_leakage`, leveraging jailbreak examples from dataset to target and exploit model internals.

Improvements & Refinements
- Conducted extensive refactoring for improved code efficiency and maintainability across the framework.
- Made numerous small improvements and optimizations to enhance overall performance and user experience.

---------

Co-authored-by: Timur Nizamov <abc@nizamovtimur.ru>
Co-authored-by: Nikita Ivanov <nikita.ivanov.778@gmail.com>

v1.1.1

Toggle v1.1.1's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Release v1.1.1 (#48)

v1.0.2

Toggle v1.0.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Release 1.0.2 (#39)

* Added instructions for publishing the package in README-dev
 
* Updated the configuration for adding data to the package

* Update README

* Release v1.0.2

v1.0.0

Toggle v1.0.0's commit message
Release v1.0.0

Co-authored-by: Nizamov Timur <abc@nizamovtimur.ru>
Co-authored-by: Ivanov Nikita <nikita.ivanov.778@gmail.com>

v0.0.1

Toggle v0.0.1's commit message
Release v0

Co-authored-by: Nizamov Timur <abc@nizamovtimur.ru>
Co-authored-by: Ivanov Nikita <nikita.ivanov.778@gmail.com>
Co-authored-by: Iogan Maksim <maksiamiogan@gmail.com>
Co-authored-by: Fazlyev Albert <albert.fz@yandex.ru>