Be Kind, Rewrite: Benign Projections Via Rewriting Defend against LLM Data Poisoning Attacks

Large language models LLMs are highly susceptible to backdoor attacks BAs, wherein training samples are poisoned using trigger-based harmful content. Furthermore, existing defenses have proven ineffective when extensively tested across BA patterns. To better combat BAs, we explore the use of LLM...

Machine Learning Engineering Open Book 安全漏洞

Machine Learning Engineering Open Book is a collection of methodologies for training and fine-tuning large language models developed by Stas Bekman. There is a security vulnerability in Machine Learning Engineering Open Book. This vulnerability arises from the use of the torch-checkpoint-shrink.p...

Shuffling Cards When You Are of Very Little Brain: Low Memory Generation of Permutations

How can we generate a permutation of the numbers $1$ through $n$ so that it is hard to guess the next element given the history so far? The twist is that the generator of the permutation the "Dealer" has limited memory, while the "Guesser" has unlimited memory. With unbounded memory actually $n$...