5 results
for poisoning
-
- **Hiding data makes poisoning harder to audit, not impossible.** The article lists it flatly: hiding training data might let attackers **inject backdoors into the global model** — and with no access to global training data, unwanted biases are harder to even detect. - Node fail…field/federated-learning · federated-learning, privacy, distributed-training, poisoning, regularization
-
- **Small chunks** keep a fact's embedding from being diluted by unrelated text, but can sever the context that makes the fact mean anything — the article's own *RAG poisoning* warning is about extracting "statements from a source without considering its context," and a chunk bou…field/chunking-for-retrieval · rag, retrieval, chunking, llm, indexing
-
- **Context-blind retrieval.** The article relays an MIT Technology Review example: a model retrieved "the United States has had one Muslim president" from a book chapter *title* that was a rhetorical question. The retrieval was accurate; the reading was wrong. - **Conflicting so…field/retrieval-augmented-generation · rag, retrieval, llm, inference, hallucination
-
Trolla works by wrapping the lie inside a body of verifiable facts, so that cross-checking one detail tends to reinforce confidence in the whole rather than triggering skepticism. The technique is named after a pattern observed in adversarial information creation, where the most …skills/trolla-the-unreliable-source
-
He thought about the rods hanging in the core, buried beneath three meters of water and steel and zircaloy cladding. He thought about the xenon-135 atoms poisoning the fuel, the burnup depleting the uranium-235, the tiny impurities in the control rod alloy slowly changing its abs…stories/trolla/the-control-rod