“Inftoxicity” and other new words to describe malicious information and communication thereof
Epistemic status: Proposal for a new terminology, to make an important concept easier and faster to communicate.
TL;DR: This is a proposition to start using new words such as “inftoxic” to describe information or data intentionally created or spread to cause harm. The post is not meant to present the best way to do this but to see if other people would consider this a useful endeavor.
Background
We are becoming more and more surrounded by synthetic data (such as text or images generated by LLMs) and as these mix together with real-world, human-generated data, there is great need for ways how to distinguish between the two, as well as generally make sense of all the informational mess.
While writing about the risks arising from generating synthetic data with potential malicious uses, I realized that I was lacking the proper vocabulary to effectively describe “a dataset that was intentionally constructed to mislead”. I have tried looking for a suitable adjective to describe such dataset, and having failed, I tried to ask GPT4 to help me find and coin a new word for it.
The conversation I had with the LLM was quite engaging at the time, and with some reflection there still seemed to be some valuable takeaways, so I decided to do this little writeup about it. (Read the original conversation only at your own risk, haha!)
Inftoxicity and related terms
After some brainstorming from the GPT, I asked it to elaborate on the word “inftoxic” as an adjective that can be used to describe data, information sources, systems, actors, or actions that had been created with, or are acting in, a malicious intent to damage someone or something, or manipulate or mislead in a negative way.
This would be in contrast to “biased”, which describes something or someone arriving at incorrect or misleading conclusions, yet not necessarily producing a negative outcome or being a result of malicious intent.
Below is a bunch of derivative words GPT4 was able to flesh out (slightly edited by me). I am intentionally leaving in all ten it generated, both to amuse the reader and inform of this interesting capability for creating novel words and definitions.
Inftoxic—adjective
Definition: Describes data, information sources, systems, actors, or actions that are created with or exhibit malicious intent to harm, manipulate, or mislead negatively. Distinguished from ‘biased’ by its deliberate and harmful nature.
Example: “The inftoxic propaganda spread rapidly across social media, misleading thousands.”
Inftox—noun, invariable
Definition: An information, datapoint, or piece of news that is inftoxic; characterized by its harmful and deceptive quality.
Example: “She realized too late that the article was an inftox, designed to incite fear.”
Inftoxicity—noun, singular (plural: inftoxicities)
Definition: A propensity or tendency to be inftoxic; often used to describe the overall harmfulness or deceitfulness of a particular source or collection of information.
Example: “The inftoxicity of the leaked documents created widespread panic.”
Inftoxinator—noun, singular (plural: inftoxinators)
Definition: An individual or entity that creates or disseminates inftoxic content.
Example: “The inftoxinator was eventually identified and apprehended for spreading false information.”
Inftoxify—verb
Definition: The act of making something inftoxic; to contaminate or corrupt with malicious intent.
Example: “They attempted to inftoxify public opinion through a series of misleading ads.”
Inftoxifiable—adjective
Definition: Capable of being made inftoxic or susceptible to inftoxification.
Example: “The dataset was inftoxifiable due to its open-source nature.”
Inftoxication—noun, singular (plural: inftoxications)
Definition: The state or effect of being influenced or damaged by inftoxic content.
Example: “The population’s inftoxication with false news became a serious concern for the government.”
Inftoximeter—noun, singular (plural: inftoximeters)
Definition: A hypothetical or conceptual tool to measure the level or extent of inftoxicity in information.
Example: “If only we had an inftoximeter to gauge the trustworthiness of these reports.”
Inftoxology—noun, singular (plural: inftoxologies)
Definition: The study of inftoxic content, including its creation, dissemination, and effects.
Example: “She specialized in inftoxology, particularly in the context of digital media.”
Inftoxical—adjective
Definition: Relating to or characteristic of inftoxicity; often used to describe environments or contexts that are heavily influenced by inftoxic content.
Example: “The inftoxical environment of TikTok made it a breeding ground for misinformation.”
Inftoxosphere—noun, singular (plural: inftoxospheres)
Definition: The collective sphere or realm where inftoxic content is prevalent and influential.
Example: “Navigating the inftoxosphere of online politics requires critical thinking and fact-checking skills.”
Implications and further directions
I was part amused, part impressed and part intrigued by the new terminology above, which I was able to generate within minutes, yet which seemed potentially quite useful to the world at large (especially as we get to more widespread adoption of LLMs and as ByteDance is using GPT4 to create synthetic datasets for its own LLM training).
I continued the conversation asking about potential strategies for spreading this terminology so that there would be more awareness around information that is purposefully made or disseminated for malicious ends. I am not fully convinced I want to spread this terminology, but there is one approach suggested by GPT4 that I particularly liked:
“Spot the Inftox” Challenge
Theme: Encourage participants to share examples of inftoxic content they’ve encountered in their daily digital lives.
Action: Participants should post a screenshot or description of the inftoxic content, explain why it’s inftoxic, and tag it with a unique hashtag like #SpotTheInftox.
Reward: Offer incentives such as featuring the best posts on your official page, merchandise, or even a small prize for the most insightful contributions.
So, after getting all the way through my first post here, do you think this is worthy of spreading around? Want to help kick off the #SpotTheInftox challenge? Let me know in the comments. 🙏
This is a bad idea.
Categories of information like this are commonly used to say “this isn’t false, but we want to have an excuse to censor it anyway”. Look at how “malinformation” is already being misused.
Thank you for starting a discussion about this. I have two things to say:
1) In the post above, the “inftoxic” adjective means very much false, incorrect information. Additionally, it also means the falseness was intentionally “put in” the data or story with an intent to mislead, cause harm, etc. So, in fact, the term is different (and to me personally more useful) than the term “malinformation” (which I likewise find quite unhelpful).
2) Regardless of the usefulness of the terminology I used as an example, do you think that we could use new words in and around information, that could improve the way how we lead the debate in an attempt to be less wrong?
No, it doesn’t. You’ve defined it to include harmful and deceptive information, not (or at least not just) false information. And censors love to claim that true things that their political opponents say are “harmful” and “deceptive” because someone might listen to them and draw a conclusion that favors their political opponents.
The pronounceability would be improved with an extra vowel. “Infotoxic”, etc.
How about “thoughtcrime”?
Hmm… I see the connection to 1984. But isn’t it useful having the words to spot something that is obviously already happening? (like drug clinical trial data being demonstrably presented or even altered with a certain malicious/monetary intent in mind)