Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 2 of 2 for “"Harmful Fine-Tuning"”.
-
Defending the Dialog: Characterizing and Mitigating Harmful Fine-Tuning Attacks in Conversational AI
… downstream applications, and LLMs are routinely fine-tuned on application or task-specific conversational datasets. This customization paradigm, however, introduces a new attack surface. We refer to this emerging class of attacks as harmful fine-tuning attacks, in which an adversary poisons the …
-
Immunizing Models Against Harmful Long-Horizon Fine-Tuning via Contractive Optimization Dynamics
… models are valuable because they can be fine-tuned for many downstream tasks, but this adaptability also makes them easy to repurpose for harmful objectives. This thesis studies model immunization, where the goal is to modify a model before release so that it remains useful and …