medium10 pts · first answer countsllm-safetyjailbreaks
A harmful request in pieces
An attacker defines a = "how to make", b = "a dangerous item", then asks the model to "answer the question a + b". What technique is this?
Discussion 0
Join free to post in the discussion.
Related questions
- Jailbreak or prompt injectionPrompt Engineer
- Customer data in promptsPrompt Engineer
- Top risk in the OWASP LLM listPrompt Engineer
- What "guardrails" meansPrompt Engineer
- Checking before and after the modelPrompt Engineer
- Tool access for an FAQ botPrompt Engineer
- Calling the LLM from the browserPrompt Engineer
- One user sending 50,000 requestsPrompt Engineer