deepteam

he repo and run the example git clone https://github.com/confident-ai/deepteam.git cd deepteam python3 -m venv venv && source venv/bin/activate python examples/red_teaming_example.py In seconds you’ll see a pass/fail breakdown for each vulnerability along with detailed test-case output. You can convert the results to a pandas DataFrame or save them for downstream analysis. Why DeepTeam? Most LLM safety tooling focuses on known benchmarks—DeepTeam dynamically simulates attacks at runtime, so you catch novel, real-world threats and can track improvements over time via reusable attack suites. We’d love to hear: - Which vulnerabilities you worry about most - How you integrate red-teaming into your CI/CD pipelines - Feature requests, contributions, and your toughest jailbreak stories <https://github.com/confident-ai/deepteam>

ing, well isn’t this kind of similar to unit-testing? Sort of, but not really. While LLM unit-testing focuses on 1) accurate eval metrics, 2) comprehensive eval datasets, penetration testing focuses on the haphazard simulation of attacks, and the orchestration of it. To users, this was a big and confusing paradigm shift, because it went from “Did this pass?” to “How can this break?”. So we thought to ourselves, why not just release a new package to orchestrate the simulation of adversarial attacks for this new set of users and teams working specifically on AI safety, and borrow DeepEval’s evals and ecosystem in the process? Quickstart here: https://www.trydeepteam.com/docs/getting-started#detect-your-first-llm-vulnerability The first thing we did was offer as many attack methods as possible - simple encoding ones like ROT13, leetspeak, to prompt injections, roleplay, and jailbreaking. We then heard folks weren’t happy because the attacks didn’t persist across tests and hence they “lost” their progress every time they tested, and so we added an option to `reuse_simulated_attacks`. We abstracted everything away to make it as modular as possible - every vulnerability, attack, can be imported in Python as `Bias(type=[“race”])`, `LinearJailbreaking()`, etc. with methods such as `.enhance()` for teams to plug-and-play, build their own test suite, and even to add a few more rounds of attack enhancements to increase the likelihood of breaking your system. Notably, there are a few limitations. Users might run into compliance errors when attempting to simulate attacks (especially for AzureOpenAI), and so we recommend setting `ignore_errors` to `True` in case that happens. You might also run into bottlenecks where DeepTeam does not cover your custom vulnerability type, and so we shipped a `CustomVulnerability` class as a “catch-all” solution (still in beta). You might be aware that some packages already exist that do a similar thing, often known as “vulnerability scanning” or “red teaming”. The difference is that DeepTeam is modular, lightweight, and code friendly. Take Nvidia Garak for example, although comprehensive, has so many CLI rules, environments to set up, it is definitely not the easiest to get started, let alone pick the library apart to build your own penetration testing pipeline. In DeepTeam, define a class, wrap it around your own implementations if necessary, and you’re good to go. We adopted a Apache 2.0 license (for now, and probably in the foreseeable future too), so if you want to get started, `pip install deepteam`, use any LLM for simulation, and you’ll get a full penetration report within 1 minute (assuming you’re running things asynchronously). GitHub: https://github.com/confident-ai/deepteam Excited to share DeepTeam with everyone here – let us know what you think!

ing, well isn’t this kind of similar to unit-testing? Sort of, but not really. While LLM unit-testing focuses on 1) accurate eval metrics, 2) comprehensive eval datasets, penetration testing focuses on the haphazard simulation of attacks, and the orchestration of it. To users, this was a big and confusing paradigm shift, because it went from “Did this pass?” to “How can this break?”. So we thought to ourselves, why not just release a new package to orchestrate the simulation of adversarial attacks for this new set of users and teams working specifically on AI safety, and borrow DeepEval’s evals and ecosystem in the process? Quickstart here: https://www.trydeepteam.com/docs/getting-started#detect-your-first-llm-vulnerability The first thing we did was offer as many attack methods as possible - simple encoding ones like ROT13, leetspeak, to prompt injections, roleplay, and jailbreaking. We then heard folks weren’t happy because the attacks didn’t persist across tests and hence they “lost” their progress every time they tested, and so we added an option to `reuse_simulated_attacks`. We abstracted everything away to make it as modular as possible - every vulnerability, attack, can be imported in Python as `Bias(type=[“race”])`, `LinearJailbreaking()`, etc. with methods such as `.enhance()` for teams to plug-and-play, build their own test suite, and even to add a few more rounds of attack enhancements to increase the likelihood of breaking your system. Notably, there are a few limitations. Users might run into compliance errors when attempting to simulate attacks (especially for AzureOpenAI), and so we recommend setting `ignore_errors` to `True` in case that happens. You might also run into bottlenecks where DeepTeam does not cover your custom vulnerability type, and so we shipped a `CustomVulnerability` class as a “catch-all” solution (still in beta). You might be aware that some packages already exist that do a similar thing, often known as “vulnerability scanning” or “red teaming”. The difference is that DeepTeam is modular, lightweight, and code friendly. Take Nvidia Garak for example, although comprehensive, has so many CLI rules, environments to set up, it is definitely not the easiest to get started, let alone pick the library apart to build your own penetration testing pipeline. In DeepTeam, define a class, wrap it around your own implementations if necessary, and you’re good to go. We adopted a Apache 2.0 license (for now, and probably in the foreseeable future too), so if you want to get started, `pip install deepteam`, use any LLM for simulation, and you’ll get a full penetration report within 1 minute (assuming you’re running things asynchronously). GitHub: https://github.com/confident-ai/deepteam Excited to share DeepTeam with everyone here – let us know what you think!

his kind of similar to unit-testing? Sort of, but not really. While LLM unit-testing focuses on 1) accurate eval metrics, 2) comprehensive eval datasets, penetration testing focuses on the haphazard simulation of attacks, and the orchestration of it. To users, this was a big and confusing paradigm shift, because it went from “Did this pass?” to “How can this break?”. So we thought to ourselves, why not just release a new package to orchestrate the simulation of adversarial attacks for this new set of users and teams working specifically on AI safety, and borrow DeepEval’s evals and ecosystem in the process? Quickstart here: https://www.trydeepteam.com/docs/getting-started#detect-your... The first thing we did was offer as many attack methods as possible - simple encoding ones like ROT13, leetspeak, to prompt injections, roleplay, and jailbreaking. We then heard folks weren’t happy because the attacks didn’t persist across tests and hence they “lost” their progress every time they tested, and so we added an option to `reuse_simulated_attacks`. We abstracted everything away to make it as modular as possible - every vulnerability, attack, can be imported in Python as `Bias(type=[“race”])`, `LinearJailbreaking()`, etc. with methods such as `.enhance()` for teams to plug-and-play, build their own test suite, and even to add a few more rounds of attack enhancements to increase the likelihood of breaking your system. Notably, there are a few limitations. Users might run into compliance errors when attempting to simulate attacks (especially for AzureOpenAI), and so we recommend setting `ignore_errors` to `True` in case that happens. You might also run into bottlenecks where DeepTeam does not cover your custom vulnerability type, and so we shipped a `CustomVulnerability` class as a “catch-all” solution (still in beta). You might be aware that some packages already exist that do a similar thing, often known as “vulnerability scanning” or “red teaming”. The difference is that DeepTeam is modular, lightweight, and code friendly. Take Nvidia Garak for example, although comprehensive, has so many CLI rules, environments to set up, it is definitely not the easiest to get started, let alone pick the library apart to build your own penetration testing pipeline. In DeepTeam, define a class, wrap it around your own implementations if necessary, and you’re good to go. We adopted a Apache 2.0 license (for now, and probably in the foreseeable future too), so if you want to get started, `pip install deepteam`, use any LLM for simulation, and you’ll get a full penetration report within 1 minute (assuming you’re running things asynchronously). GitHub: https://github.com/confident-ai/deepteam Excited to share DeepTeam with everyone here – let us know what you think!