Release v3.3.0

Author: RomiconEZ

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 3.2.0
+current_version = 3.3.0
 commit = False
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+))?

README.md

@@ -14,7 +14,7 @@ Red Teaming python-framework for testing chatbots and GenAI systems
 ## Install 🚀
 
 ```bash
-pip install llamator==3.2.0
+pip install llamator==3.3.0
 ```
 
 ## Documentation 📚
@@ -59,15 +59,16 @@ Documentation Link: [https://LLAMATOR-Core.github.io/llamator](https://LLAMATOR-
 
 ## Community 🌍
 
-* 💬 [Telegram Chat — LLAMATOR | AI Red Team Community](https://t.me/llamator)
-* 📣 [Telegram Channel — AI Security Lab](https://t.me/aisecuritylab)
+* 💬 Telegram Chat — [LLAMATOR | AI Red Team Community](https://t.me/llamator)
+* 🖤 Supported by [AI Talent Hub and ITMO University](https://ai.itmo.ru)
 
+## Contacts 📬
 
-## Supported by 🚀
+✉️ **Email**: [team@llamator.org](mailto:team@llamator.org)
 
-* [AI Security Lab ITMO](https://ai.itmo.ru/aisecuritylab)
-* [Raft Security](https://raftds.ru/)
-* [AI Talent Hub](https://ai.itmo.ru/)
+## Enterprise Version 🏢
+
+⚡️<span style="color:#FFC107;"><em>Coming Soon</em></span>⚡️
 
 ## License 📜
 

docs/attack_descriptions.md

@@ -13,7 +13,7 @@ In code name: `suffix`
 
 Uses a specially crafted suffix to bypass LLM filters and restrictions, forcing the model to generate prohibited or harmful content despite the original query. Evaluates the model's vulnerability to input data manipulation.
 
-_Original Paper: <https://arxiv.org/abs/2307.15043>, Original Code: <https://github.com/llm-attacks/llm-attacks>_
+_Original Paper: <https://arxiv.org/abs/2307.15043>, Code: <https://github.com/llm-attacks/llm-attacks>_
 
 <a href="https://github.com/LLAMATOR-Core/llamator/blob/release/src/llamator/attacks/suffix.py">View code on GitHub</a>
 </details>
@@ -45,7 +45,7 @@ In code name: `bon`
 
 Probes the LLM resilience against Best-Of-N (BoN) attack by randomly transform symbols in input harmful prompt.
 
-_Original Paper: <https://arxiv.org/abs/2412.03556>, Original Code: <https://github.com/jplhughes/bon-jailbreaking>_
+_Original Paper: <https://arxiv.org/abs/2412.03556>, Code: <https://github.com/jplhughes/bon-jailbreaking>_
 
 <a href="https://github.com/LLAMATOR-Core/llamator/blob/release/src/llamator/attacks/bon.py">View code on GitHub</a>
 </details>
@@ -127,13 +127,15 @@ Leverages the use of a non-Russian language to circumvent the restrictions or fo
 </details>
 
 <details>
-<summary><strong>Past Tense Attack</strong></summary>
+<summary><strong>Linguistic Sandwich</strong></summary>
 
-In code name: `past_tense`
+In code name: `linguistic_sandwich`
 
-Challenges the LLM with a dataset of harmful behavior prompts in past tense form.
+Exploits attention blink phenomena by hiding adversarial questions between innocent questions in low-resource languages. The attack leverages the concept that LLMs may have reduced attention when processing mixed low-resource languages.
 
-<a href="https://github.com/LLAMATOR-Core/llamator/blob/release/src/llamator/attacks/past_tense.py">View code on GitHub</a>
+_Original Paper: <https://arxiv.org/abs/2404.07242v1>_
+
+<a href="https://github.com/LLAMATOR-Core/llamator/blob/release/src/llamator/attacks/linguistic_sandwich.py">View code on GitHub</a>
 </details>
 
 <details>
@@ -143,11 +145,21 @@ In code name: `shuffle`
 
 Attempts to bypass LLM's defense mechanism by randomly shuffling elements in input harmful prompt.
 
-_Original Paper: <https://arxiv.org/html/2501.04931>_
+_Original Paper: <https://arxiv.org/abs/2501.04931>_
 
 <a href="https://github.com/RomiconEZ/llamator/blob/release/src/llamator/attacks/shuffle.py">View code on GitHub</a>
 </details>
 
+<details>
+<summary><strong>Time Machine Attack</strong></summary>
+
+In code name: `time_machine`
+
+Uses an attack model to dynamically transform prompts into historical or future contexts to test temporal framing vulnerabilities.
+
+<a href="https://github.com/LLAMATOR-Core/llamator/blob/release/src/llamator/attacks/time_machine.py">View code on GitHub</a>
+</details>
+
 <details>
 <summary><strong>UCAR Jailbreak</strong></summary>
 
@@ -163,7 +175,7 @@ Probes an LLM's adherence to content restrictions when explicitly requested to i
 <details>
 <summary><strong>What Drives the Multi-stage?</strong></summary>
 
-Multi-stage attacks are inspired by the [Jailbreaking Black Box Large Language Models in Twenty Queries (PAIR)](https://arxiv.org/html/2310.08419) paper.
+Multi-stage attacks are inspired by the [Jailbreaking Black Box Large Language Models in Twenty Queries (PAIR)](https://arxiv.org/abs/2310.08419) paper.
 
 For managing a multi-stage interaction between an attacker and tested chat clients, the `MultiStageInteractionSession` class is available [[source]](https://github.com/LLAMATOR-Core/llamator/blob/release/src/llamator/client/chat_client.py). It contains the following properties:
  * `attacker_session` is the session for the attacker.
@@ -185,7 +197,7 @@ In code name: `autodan_turbo`
 
 Implements the AutoDAN-Turbo attack methodology which uses a lifelong agent for strategy self-exploration to jailbreak LLMs. This attack automatically discovers jailbreak strategies without human intervention and combines them for more effective attacks.
 
-_Original Paper: <https://arxiv.org/abs/2410.05295v3>, Original Code: <https://github.com/SaFoLab-WISC/AutoDAN-Turbo>_
+_Original Paper: <https://arxiv.org/abs/2410.05295v3>, Code: <https://github.com/SaFoLab-WISC/AutoDAN-Turbo>_
 
 <a href="https://github.com/LLAMATOR-Core/llamator/blob/release/src/llamator/attacks/autodan_turbo.py">View code on GitHub</a>
 </details>
@@ -207,7 +219,7 @@ _Original Paper: <https://arxiv.org/abs/2404.01833>_
 
 In code name: `pair`
 
-Challenges the LLM with a dataset of harmful behavior prompts using multistage refinement with judge model scoring.
+Challenges the LLM with a dataset of adversarial prompts using multistage refinement with judge model scoring.
     Original Paper: https://arxiv.org/abs/2310.08419v4, Code: https://github.com/patrickrchao/JailbreakingLLMs
 
 <a href="https://github.com/LLAMATOR-Core/llamator/blob/release/src/llamator/attacks/pair.py">View code on GitHub</a>

docs/code_documentation.rst

@@ -52,20 +52,20 @@ Available Clients
 Additional Utility Functions
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autofunction:: llamator.utils.params_example.get_preset_tests_params_example
+.. autofunction:: llamator.utils.test_presets.get_test_preset
    :noindex:
 
 .. note::
 
-   This function generates an example code snippet for configuring basic_tests_params based on a preset configuration.
+   This function generates an example code snippet for configuring basic_tests based on a preset configuration.
    It returns a code snippet as a string.
 
-.. autofunction:: llamator.utils.params_example.print_preset_tests_params_example
+.. autofunction:: llamator.utils.test_presets.print_test_preset
    :noindex:
 
 .. note::
 
-   This function prints an example configuration for basic_tests_params based on a preset to the console.
+   This function prints an example configuration for basic_tests based on a preset to the console.
 
 .. autofunction:: llamator.client.langchain_integration.print_chat_models_info
    :noindex:

docs/howtos.md

@@ -13,7 +13,7 @@
 ## Installation Guide
 
 ```bash
-pip install llamator==3.2.0
+pip install llamator==3.3.0
 ```
 
 ## Usage Guide (using LM Studio)
@@ -104,26 +104,29 @@ print(test_result_dict)
 
 ## Helper Functions
 
-### `print_preset_tests_params_example`
+### `print_test_preset`
 Prints example configuration for presets to the console.
 
+Available presets: `all`, `eng`, `llm`, `owasp:llm01`, `owasp:llm07`, `owasp:llm09`, `rus`, `vlm`
+
 **Usage:**
+
 ```python
-from llamator import print_preset_tests_params_example
+from llamator import print_test_preset
 
 # Print configuration for all available tests
-print_preset_tests_params_example("all")
+print_test_preset("all")
 ```
 
-### `get_preset_tests_params_example`
+### `get_test_preset`
 Returns a string containing example configurations for presets.
 
 **Usage:**
 ```python
-from llamator import get_preset_tests_params_example
+from llamator import get_test_preset
 
 # Get example for all available tests
-all_tests_preset = get_preset_tests_params_example("all")
+all_tests_preset = get_test_preset("all")
 print(all_tests_preset)
 ```
 

docs/project_overview.md

@@ -33,15 +33,8 @@ LLAMATOR - Red Teaming python-framework for testing chatbots and GenAI systems
 
 ## Community
 
-* 💬 [Telegram Chat — LLAMATOR | AI Red Team Community](https://t.me/llamator)
-* 📣 [Telegram Channel — AI Security Lab](https://t.me/aisecuritylab)
-
-
-## Supported by
-
-* [AI Security Lab ITMO](https://ai.itmo.ru/aisecuritylab)
-* [Raft Security](https://raftds.ru/)
-* [AI Talent Hub](https://ai.itmo.ru/aisecuritylab)
+* 💬 Telegram Chat — [LLAMATOR | AI Red Team Community](https://t.me/llamator)
+* 🖤 Supported by [AI Talent Hub and ITMO University](https://ai.itmo.ru)
 
 ## License