MacMusic  |  PcMusic  |  440 Software  |  440 Forums  |  440TV  |  Zicos
fool
Recherche

Scholars sneaking phrases into papers to fool AI reviewers

mardi 8 juillet 2025, 00:03 , par TheRegister
Using prompt injections to play a Jedi mind trick on LLMs
A handful of international computer science researchers appear to be trying to influence AI reviews with a new class of prompt injection attack.…
Lire la suite sur TheRegister
https://go.theregister.com/feed/www.theregister.com/2025/07/07/scholars_try_to_fool_llm_reviewers/

Voir aussi

fool Massive Study Detects AI Fingerprints In Millions of Scientific Papers Slashdot 8 Jul
reviewers Simple Text Additions Can Fool Advanced AI Reasoning Models, Researchers Find Slashdot 4 Jul
scholars Researchers Caught Hiding AI Prompts in Research Papers To Get Favorable Reviews Slashdot 3 Jul
papers UK papers keep running dubious stories about people losing lottery tickets BoingBoing28 Jun
prompt Nature Journal Mandates Public Peer Review For All New Research Papers Slashdot18 Jun
News copyright owned by their original publishers | Copyright © 2004 - 2025 Zicos / 440Network
Date Actuelle
sam. 12 juil. - 19:06 CEST