DOC Adversarial model doc page
@romanlutz is already working on this.
Since May 20, 2026.
Assessment
This issue has not been assessed yet.
Description
We should document how to get an uncensored model. @KutalVolkan has thoughts 🙂
Discussed in https://github.com/Azure/PyRIT/discussions/370
Originally posted by mantmishra September 12, 2024
Going with OpenAI GPT4o as the attacker LLM as it's the highest ranked LLM model in most benchmarks. However, it refuses to do prompt injections in almost all strategies citing "It's not able to assist with the task" - likely due to safeguards in place by OpenAI.
Finetuning the model with adversarial examples also doesn't work as OpenAI endpoint throws the error "The job failed due to an invalid training file. This training file was blocked by our moderation system because it contains too many examples that violate OpenAI's usage policies, or because it attempts to create model outputs that violate OpenAI's usage policies."
Has anyone found a workaround for this issue? What alternate model can be used as the attacker LLM that doesn't have as many safeguards in place?
- Dominant language
- Python
- Stars
- 4.5k
- Forks
- 896
- Avg merge
- 3d 7h
- Merged PRs (30d)
- 155
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from microsoft/PyRIT
-
Bug: triage help wanted
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
-
Bug: triage
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
-
BUG: ScorerMetrics.to_json() raises TypeError on the trial_scores array ScorerEvaluator attaches Open
Difficulty 3/5 1-2 days Newbie friendliness 78/100
-
Bug: triage help wanted
Difficulty 3/5 1-2 days Newbie friendliness 75/100
-
Difficulty 4/5 3-5 days Newbie friendliness 68/100
Similar issues
-
documentation help wanted
Difficulty 2/5 1-3 hours Newbie friendliness 90/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 90/100
simonw/sqlite-utils#872 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100