All public logs

Combined display of all available logs of AI Wiki. You can narrow down the view by selecting a log type, the username (case-sensitive), or the affected page (also case-sensitive).

• 18:28, 14 March 2025 Alpha5 talk contribs created page Backdooring LLMs (Created page with "'''Backdooring Large Language Models (LLMs)''' refers to the process of intentionally embedding hidden, malicious behaviors—known as Backdoors—into LLMs during their training or fine-tuning phases. These Backdoors enable the model to behave normally under typical conditions but trigger undesirable outputs, such as malicious code or deceptive responses, when specific conditions or inputs are met. This phenomenon raises significant concerns about the se...")