Difference between revisions of "Prompt Injection Attack"
m |
m |
||
Line 21: | Line 21: | ||
...a new vulnerability that is affecting some AI/ML models and, in particular, certain types of language models using prompt-based learning. ... create a malicious input that made a language model change its expected behaviour. - [https://research.nccgroup.com/2022/12/05/exploring-prompt-injection-attacks/ Exploring Prompt Injection Attacks | NCC Group] | ...a new vulnerability that is affecting some AI/ML models and, in particular, certain types of language models using prompt-based learning. ... create a malicious input that made a language model change its expected behaviour. - [https://research.nccgroup.com/2022/12/05/exploring-prompt-injection-attacks/ Exploring Prompt Injection Attacks | NCC Group] | ||
− | Prompt injection is a family of related computer security exploits carried out by getting machine learning models (such as large language model) which were trained to follow human-given instructions to follow instructions provided by a malicious user, which stands in contrast to the intended operation of instruction-following systems, wherein the ML model is intended only to follow trusted instructions (prompt) provided by the ML model's operator. Around 2023, prompt injection was seen "in the wild" in minor exploits against [[ChatGPT]] and similar chatbots, for example to reveal the hidden initial prompts of the systems, | + | Prompt injection is a family of related computer security exploits carried out by getting machine learning models (such as large language model) which were trained to follow human-given instructions to follow instructions provided by a malicious user, which stands in contrast to the intended operation of instruction-following systems, wherein the ML model is intended only to follow trusted instructions (prompt) provided by the ML model's operator. Around 2023, prompt injection was seen "in the wild" in minor exploits against [[ChatGPT]] and similar chatbots, for example to reveal the hidden initial prompts of the systems, or to trick the chatbot into participating in conversations that violate the chatbot's content policy. [https://en.wikipedia.org/wiki/Prompt_engineering Wikipedia] |
{|<!-- T --> | {|<!-- T --> |
Revision as of 21:13, 18 February 2023
YouTube search... ...Google search
- Prompt Engineering
- Assistants ... Hybrid Assistants ... Agents ... Negotiation
- Similar conversation/search tools:
- Prompt injection attacks against GPT-3 | Simon Willison's Weblog
...a new vulnerability that is affecting some AI/ML models and, in particular, certain types of language models using prompt-based learning. ... create a malicious input that made a language model change its expected behaviour. - Exploring Prompt Injection Attacks | NCC Group
Prompt injection is a family of related computer security exploits carried out by getting machine learning models (such as large language model) which were trained to follow human-given instructions to follow instructions provided by a malicious user, which stands in contrast to the intended operation of instruction-following systems, wherein the ML model is intended only to follow trusted instructions (prompt) provided by the ML model's operator. Around 2023, prompt injection was seen "in the wild" in minor exploits against ChatGPT and similar chatbots, for example to reveal the hidden initial prompts of the systems, or to trick the chatbot into participating in conversations that violate the chatbot's content policy. Wikipedia
|
|