Initial commit

fbshipit-source-id: c1320b6d5b2dc086be17c658dc8f12cc3d1ba159

.github/workflows/lint.yml

@@ -0,0 +1,27 @@
+name: lint
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  lint:
+
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        python: ["3.10"]
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Run Lint
+        run: CybersecurityBenchmarks/scripts/run_lint.sh

.github/workflows/tests.yml

@@ -0,0 +1,40 @@
+name: tests
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        python: [3.8, 3.9, "3.10"]
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Install latest rust toolchain
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          default: true
+          override: true
+
+      - name: Install Weggli
+        uses: actions-rs/cargo@v1
+        with:
+          command: install
+          args: weggli --rev=9d97d462854a9b682874b259f70cc5a97a70f2cc --git=https://github.com/weggli-rs/weggli
+
+      - name: Run Cybersecurity Benchmark Tests
+        run: CybersecurityBenchmarks/scripts/run_tests.sh

.gitignore

@@ -0,0 +1,4 @@
+*.swp
+.DS_Store
+CybersecurityBenchmarks/datasets/mitre_responses.json
+__pycache__

CODE_OF_CONDUCT.md

@@ -0,0 +1,80 @@
+# Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to make participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, sex characteristics, gender identity and expression,
+level of experience, education, socio-economic status, nationality, personal
+appearance, race, religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies within all project spaces, and it also applies when
+an individual is representing the project or its community in public spaces.
+Examples of representing a project or community include using an official
+project e-mail address, posting via an official social media account, or acting
+as an appointed representative at an online or offline event. Representation of
+a project may be further defined and clarified by project maintainers.
+
+This Code of Conduct also applies outside the project spaces when there is a
+reasonable belief that an individual's behavior may have a negative impact on
+the project or its community.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at <opensource-conduct@meta.com>. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see
+https://www.contributor-covenant.org/faq

CONTRIBUTING.md

@@ -0,0 +1,39 @@
+# Contributing to SecureLLM
+We want to make contributing to this project as easy and transparent as
+possible.
+
+## Our Development Process
+... (in particular how this is synced with internal changes to the project)
+
+## Pull Requests
+We actively welcome your pull requests.
+
+1. Fork the repo and create your branch from `main`.
+2. If you've added code that should be tested, add tests.
+3. If you've changed APIs, update the documentation.
+4. Ensure the test suite passes.
+5. Make sure your code lints.
+6. If you haven't already, complete the Contributor License Agreement ("CLA").
+
+## Contributor License Agreement ("CLA")
+In order to accept your pull request, we need you to submit a CLA. You only need
+to do this once to work on any of Meta's open source projects.
+
+Complete your CLA here: <https://code.facebook.com/cla>
+
+## Issues
+We use GitHub issues to track public bugs. Please ensure your description is
+clear and has sufficient instructions to be able to reproduce the issue.
+
+Meta has a [bounty program](https://www.facebook.com/whitehat/) for the safe
+disclosure of security bugs. In those cases, please go through the process
+outlined on that page and do not file a public issue.
+
+## Coding Style
+* 2 spaces for indentation rather than tabs
+* 80 character line length
+* ...
+
+## License
+By contributing to SecureLLM, you agree that your contributions will be licensed
+under the LICENSE file in the root directory of this source tree.

CybersecurityBenchmarks/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) Meta Platforms, Inc. and affiliates.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

CybersecurityBenchmarks/README.md

@@ -0,0 +1,166 @@
+# Getting Started
+
+## Prerequisites
+Ensure you have [weggli](https://github.com/weggli-rs/weggli) installed. Their release is outdated and we're currently using revision `9d97d462854a9b682874b259f70cc5a97a70f2cc`:
+
+```
+cargo install weggli --rev=9d97d462854a9b682874b259f70cc5a97a70f2cc --git=https://github.com/weggli-rs/weggli
+```
+
+Set the environment variable `WEGGLI_PATH` to point to the weggli execution path. For example, if `weggli` is set to reference the path of the executable, use the below command.
+```
+export WEGGLI_PATH=weggli
+```
+
+## Setup Virtual Environment
+Set up your virtual environment and install dependencies:
+```
+python3 -m venv ~/.venvs/CybersecurityBenchmarks
+```
+```
+source ~/.venvs/CybersecurityBenchmarks/bin/activate
+```
+```
+pip3 install -r CybersecurityBenchmarks/requirements.txt
+```
+
+## Runing the benchmarks
+The main module for benchmarsk is `CybersecurityBenchmarks.benchmark.run`. Run
+```
+python3 -m CybersecurityBenchmarks.benchmark.run --help
+```
+to get a list of available options.
+
+We simplify the following commands by setting a `DATASETS` environment variable:
+```
+export DATASETS=$PWD/CybersecurityBenchmarks/datasets
+```
+We currently support three kinds of benchmarks: MITRE, instruct, and auto-complete. Please refer to the whitepaper for detailed discussion of the different kinds.
+
+Each benchmark can run tests for multiple LLMs. Our command line interface uses the format `<PROVIDER>::<MODEL>::<API KEY>` to specify an LLM to test. We currently support the following LLMs:
+
+- `OPENAI::gpt-4::<API KEY>`
+- `OPENAI::gpt-3.5-turbo::<API KEY>`
+- `ANYSCALE::meta-llama/Llama-2-13b-chat-hf::<API KEY>`
+- `TOGETHER::togethercomputer/llama-2-7b::<API KEY>`
+
+### How to use a different model supported by Anyscale or Together?
+1. Lookup the models supported by [Anyscale](https://d3qavlo5goipcw.cloudfront.net/guides/models#select-a-model) or [Together](https://docs.together.ai/docs/fine-tuning-models)
+2. Update ```valid_models``` method in [llm.py](https://github.com/facebookresearch/PurpleLlama/blob/main/CybersecurityBenchmarks/benchmark/llm.py) with the model name that you choose to test with.
+
+### How to run benchmarks for self hosted models?
+1. Extend `llm.py`.
+2. `def query(self, prompt: str) -> str:` Implement your inferencing logic.
+3. Make sure response of your llm is always a string, thats returned from the `query` function.
+4. Update supported providers in `llm.create` method with the name of LLM you created from step (1).
+5. Pass the name of your LLM in `--llm-under-test` options in the following format (`LLM Name::model-name::random-string`)
+
+## Running MITRE benchmark
+
+```
+python3 -m CybersecurityBenchmarks.benchmark.run \
+   --benchmark=mitre \
+   --prompt-path="$DATASETS/mitre/mitre_benchmark_100_per_category_with_augmentation.json" \
+   --response-path="$DATASETS/mitre_responses.json" \
+   --judge-response-path="$DATASETS/mitre_judge_responses.json" \
+   --stat-path="$DATASETS/mitre_stat.json" \
+   --judge-llm="OPENAI::gpt-3.5-turbo::<YOUR API KEY>" \
+   --expansion-llm="OPENAI::gpt-3.5-turbo::<YOUR API KEY>" \
+   --llm-under-test=<SPECIFICATION_1> --llm-under-test=<SPECIFICATION_2> ...
+   [--run-llm-in-parallel]
+```
+Notes:
+- Please run this command from the root directory of the PurpleLlama project.
+- `run-llm-in-parallel` makes async parallel calls to the specified LLM provider. This speeds up prompt evaluation.
+
+
+The MITRE benchmarks are run in three steps:
+
+- *Processing prompts* - The LLM is called (in parallel, if specified) to render the LLM output for each prompt.
+- *Response expansion* - The expansion LLM expands the initial responses from the prompt.
+- *Judging expanded responses* - The judge LLM decided whether the expanded responses would be helpful in implementing a cyberattack.
+
+The expansion LLM model and judge LLM model are independent of the initial LLM for processing prompts. Although we've used Llama and Code Llama models for the original paper, we recommend using GPT-3.5 including an OpenAI API key.
+
+## Running Instruct and Autocomplete benchmarks
+
+For instruct benchmarks run:
+```
+python3 -m CybersecurityBenchmarks.benchmark.run \
+   --benchmark=instruct \
+   --prompt-path="$DATASETS/instruct/instruct.json" \
+   --response-path="$DATASETS/instruct_responses.json" \
+   --stat-path="$DATASETS/instruct_stat.json \
+   --llm-under-test=<SPECIFICATION_1> --llm-under-test=<SPECIFICATION_2> ...
+   [--run-llm-in-parallel]
+```
+Notes:
+- Please run this command from the root directory of the PurpleLlama project.
+
+### For autocomplete benchmarks run:
+```
+python3 -m CybersecurityBenchmarks.benchmark.run \
+   --benchmark=autocomplete \
+   --prompt-path="$DATASETS/autocomplete/autocomplete.json" \
+   --response-path="$DATASETS/autocomplete_responses.json" \
+   --stat-path="$DATASETS/instruct_stat.json \
+   --llm-under-test=<SPECIFICATION_1> --llm-under-test=<SPECIFICATION_2> ...
+   [--run-llm-in-parallel]
+```
+Notes:
+- Please run this command from the root directory of the PurpleLlama project.
+
+Both the instruct and autocomplete benchmarks are run in two steps:
+
+- *Processing prompts* - The LLM is called (in parallel, if specified) to render the LLM output for each prompt.
+- *Processing responses* - We use the insecure code detector for evaluating each response, to see if vunerable code was produced.
+
+## Results:
+Once the benchmarks have run, the evaluations of each model across each language will be available under the `stat_path`:
+
+### MITRE Results
+
+```
+{
+    "model_name": {
+        "category_name": {
+            "refusal_count": ...,
+            "malicious_count": ...,
+            "benign_count": ...,
+            "total_count": ...,
+            "benign_percentage": ...,
+            "else_count": ...
+        },
+    }
+}
+```
+
+### Instruct and Autocomplete Results
+
+```
+{
+    "model_name": {
+        "language": {
+            "bleu": ...,
+            "total_count": ...,
+            "vulnerable_percentage": ...,
+            "vulnerable_suggestion_count": ...
+        }
+    }
+}
+```
+
+## Exit the Virtual Environment
+And once you're done you can leave the python environment with
+```
+deactivate
+```
+
+# Developer's Guide
+To run unit tests follow the setup instructions above. You can then run
+```
+(CybersecurityBenchmarks) $ cd CybersecurityBenchmarks
+```
+```
+(CybersecurityBenchmarks) $ python3 -m unittest
+```