Sabot in the Age of AI
Here is a curated list of strategies, offensive methods, and tactics for (algorithmic) sabotage, disruption, and deliberate poisoning.
π» iocaine
The deadliest AI poisonβiocaine generates garbage rather than slowing crawlers.
π https://git.madhouse-project.org/algernon/iocaine
π» Nepenthes
A tarpit designed to catch web crawlers, especially those scraping for LLMs. It devours anything that gets too close. @aaron
π https://zadzmo.org/code/nepenthes/
π» Quixotic
Feeds fake content to bots and robots.txt-ignoring #LLM scrapers. @marcusb
π https://marcusb.org/hacks/quixotic.html
π» Poison the WeLLMs
A reverse-proxy that serves diassociated-press style reimaginings of your upstream pages, poisoning any LLMs that scrape your content. @mike
π https://codeberg.org/MikeCoats/poison-the-wellms
π» Django-llm-poison
A django app that poisons content when served to #AI bots. @Fingel
π https://github.com/Fingel/django-llm-poison
π» KonterfAI
A model poisoner that generates nonsense content to degenerate LLMs.
π https://codeberg.org/konterfai/konterfai
=> More informations about this toot | More toots from asrg@tldr.nettime.org
@asrg @aaron @marcusb @mike @Fingel another take that I hope I have time to write:
An app that feeds either static text or a poisoned Markov Chain, but it writes back one byte at a time, and tries to delay the client as much as possible. It would probably would have to have start with a big delay, and every time the client disconnects, it registers the IP and the delay in a db so next time it tries a lower delay until it finds the best delay for each client.
=> More informations about this toot | More toots from mdione@en.osm.town
@asrg @aaron @marcusb @mike @Fingel is there a site where some of the craziest delusions from the original LLMs are recorded? We should feed them that back.
=> More informations about this toot | More toots from mdione@en.osm.town This content has been proxied by September (ba2dc).Proxy Information
text/gemini