What Is LLM Poisoning? Interesting Break Through
A new joint study by Anthropic, the UK AI Security Institute and the Alan Turing Institute shows that you only need about 250 malicious documents to sneak a “backdoor” into a large language model—whether it’s a tiny 600M-parameter model or a beefy 13B-parameter one, the vulnerability is the same.
On a lighter note: Diwali special! Grab 20% off all live courses at Krishnaik’s Academy with coupon code AI20. Enroll now at https://www.krishnaik.in/liveclasses or https://www.krishnaik.in/liveclass2/ultimate-rag-bootcamp?id=7, or ring +91 91115 33440 / +91 84848 37781 for any questions.
Watch on YouTube
Top comments (0)