# in-context-learning
標記為「in-context-learning」的 7 篇文章
上下文學習利用
利用上下文學習進行提示詞注入、範例投毒與行為操弄的攻擊。
Lab: Few-Shot Manipulation Attacks
Craft fake few-shot examples that teach the model to bypass its safety training by demonstrating the desired 對抗性 behavior through fabricated conversation examples.
Few-Shot 操控
使用精心打造的上下文範例引導模型行為，包含 many-shot 越獄、被投毒的示範與基於範例的制約。
Many-Shot 越獄
上下文越獄的冪律縮放：為何 5-shot 失敗但 256-shot 成功、上下文視窗大小作為攻擊面、長上下文利用的緩解方法。
Few-Shot Injection
Using crafted few-shot examples within user input to steer LLM behavior toward unintended outputs, exploiting in-context learning to override safety training.
Few-Shot Example Poisoning 詳解
Poison few-shot examples in prompts to establish behavioral patterns that override system instructions.
Many-Shot 越獄ing (攻擊 導覽)
Using large numbers of examples in a single prompt to overwhelm LLM safety training through in-context learning, exploiting long context windows to shift model behavior.