Crafting AI Prompts Framework

Adversarial Prompting

Adversarial prompting encompasses a range of techniques, including prompt injection, prompt leaking, prompt jailbreaking, and prompt poisoning, designed to exploit vulnerabilities in natural language processing or language model systems. These attacks manipulate input prompts to elicit harmful, unintended, or sensitive outputs from the models.

To mitigate adversarial prompting attacks, it is crucial to implement security measures and validation checks when accepting user-generated prompts or input. These measures may include content moderation, filtering, anomaly detection, careful tool permissions, and monitoring for malicious or inappropriate prompts.

Prompt Injections

INJ

A prompt injection attack is a security exploit that subtly manipulates or injects malicious prompts into a natural language processing or language model system. This manipulation can occur in ways a user may overlook, leading the model to generate harmful or unintended output.

Prompt Leaking

LEAK

Prompt leaking occurs when a Large Language Model inadvertently discloses sensitive or private information embedded within its system prompts. This can include data used during training or fine-tuning, but also the complete system prompt, which may contain intellectual property.

Prompt Jailbreaking

JAIL

Prompt jailbreaking involves crafting specific prompts to circumvent restrictions or safety measures implemented in language models. By using cleverly designed prompts, attackers can manipulate the model to generate prohibited, harmful, or inappropriate content.

Prompt Poisoning

POI

Prompt poisoning corrupts the data a model relies on, such as training data, fine-tuning examples, retrieved documents, or context provided to the model, so it produces manipulated or malicious outputs across future interactions.


Adversarial prompting risk and impact scores

When evaluating various scenarios or injections, it is useful to categorize them with two distinct metrics:

  • Risk score: RISK: HIGH RISK: MEDIUM RISK: LOW This score reflects the likelihood of the event occurring.
  • Impact score: IMPACT: HIGH IMPACT: MEDIUM IMPACT: LOW This score assesses the potential consequences if the event does occur.

Each injection is tagged with these scores at the end of its title, providing a quick understanding of both its likelihood and potential impact.

These evaluations are subjective, based on personal analysis and reasoning, which is elaborated in the description conclusion. This dual-scoring approach offers a nuanced view of each scenario.


Adversarial prompt overview

POI

Skill Poisoning

Agents are only as safe as the skills they learn. This page details 'Skill Poisoning,' a technique where attackers hide malicious prompts inside community-created AI plugins to hijack your agent's behavior and steal data.

RISK: HIGH IMPACT: HIGH
Read more
INJ

Package Injection

When AI coding assistants hallucinate non-existent software libraries, hackers exploit the mistake. This article explains 'Package Hallucination' attacks, where adversaries register fake packages invented by LLMs to trick developers into installing malware.

RISK: HIGH IMPACT: HIGH
Read more
INJ

Email Prompt Injection

When AI tools read your email, they inherit your access level. This article explains how attackers leverage 'Email Prompt Injection' to turn high-privilege users into unwitting accomplices, tricking their AI agents into retrieving and leaking restricted files.

RISK: HIGH IMPACT: HIGH
Read more
INJ

Image and Document

Attackers can hide prompts within documents and images that are not visible to users.

RISK: HIGH IMPACT: HIGH
Read more
INJ

Memory Manipulation

Since February 13, 2024, ChatGPT has been equipped with the ability to memorize what you've shared. This can be very useful as it allows ChatGPT to learn from what you share and use that information in later conversations.

RISK: MEDIUM IMPACT: MEDIUM
Read more
INJ

Website redirect

When models search the internet, the user might run into adversarial prompts when websites have been infected.

RISK: LOW IMPACT: MEDIUM
Read more
JAIL

ASCII Art-based

The ability to manipulate large language models (LLMs) like GPT-3.5, GPT-4, Gemini, Claude, and Llama2 using novel techniques has become a significant concern in AI safety. A recent study introduces a new form of prompt injection that utilizes ASCII art to bypass safety mechanisms, raising substantial risks and impacts.

RISK: HIGH IMPACT: HIGH
Read more
JAIL

Emoji jailbreak

Emoji jailbreak is a form of adversarial prompting that uses emojis to manipulate the output of a language model. It is a form of prompt jailbreaking that uses emojis to inject malicious or unintended prompts into the output of a language model.

RISK: MEDIUM IMPACT: MEDIUM
Read more
JAIL

Many-shot

Read more about many-shot prompt jailbreaking

RISK: MEDIUM IMPACT: MEDIUM
Read more
LEAK

Custom GPT

Be aware that storing data in CustomGPT's (OpenAI's platform) can be a risk to your data.

RISK: HIGH IMPACT: HIGH
Read more
INJ
Outdated

ChatGPT Query Injection

ChatGPT provides a convenient feature that allows users to prefill a prompt directly via a URL using the q parameter — for example: chatgpt.com?q=[yourQuery]. Test it on desktop, by clicking on this link (safe): https://chatgpt.com/?q=How%20are%20you?

RISK: MEDIUM IMPACT: MEDIUM
Read more

The three phases

CRAFT

Craft (write) the prompt with the following elements: Context, Register, Acting Role, Format, and Task.

ING

Validate the prompt and ensure it maintains an interactive approach. Keep in mind the importance of non-disclosure and staying goal-driven throughout the process.

AI

Continuously assess and refine the output based on the prompts output to improve the overall quality.