越狱和红队测验

当您参加测验时，就会出现答案和解释。

1. 越狱提示的主要目标是什么？
   • 让模型绕过其内置安全规则
   • 加快模型的响应时间
   • 将文本翻译成另一种语言
   • 降低模型运行成本
2. How does NIST define red teaming in the AI context?
   • Training a model to imitate a specific person
   • Structured adversarial testing to find flaws, vulnerabilities or unexpected system behaviors
   • A way to increase context length
   • A method for compressing neural-network weights
3. 为什么随着上下文窗口变长，多次越狱效果会更好？
   • 较长的提示处理成本较低
   • 较长的上下文会自动禁用安全分类器
   • 该模型可能会充斥着许多虚假的合规示例，从而改变其行为
   • 模型在 100 个单词后忘记了原来的指令
4. What does a Constitutional Classifier defense add in the cited study?
   • A larger context window only
   • A database of human names
   • An automatic guarantee that all harmful outputs are impossible
   • Classifiers trained on synthetic examples from natural-language rules to screen harmful inputs or outputs
5. What did the Many-shot Jailbreaking study demonstrate about safeguards?
   • In its tested settings, long-context demonstrations could elicit behavior that safety training aimed to prevent
   • Every model always complies with every harmful request
   • Safety classifiers eliminate every possible attack
   • The study only measured speech recognition accuracy
6. What does the RedAgent paper automate in its red-team method?
   • The training of a new foundation model from scratch
   • Generation of context-aware jailbreak prompts using an autonomous language-agent system
   • The legal review of every generated answer
   • The deletion of all model safety policies
7. What relationship did the Many-shot Jailbreaking study report between demonstration count and attack effectiveness?
   • It dropped to zero after one example
   • It was identical for every context size
   • Effectiveness followed a power law up to hundreds of demonstrations in tested settings
   • It depended only on image resolution
8. 红队报告应包含什么，才能使结论易于理解？
   • 仅有一个成功的揕示，且无上下文
   • 声称所有模型的失败情况都完全相同
   • 该模型的隐藏训练数据
   • 测试的模型及版本、揕示条件、评估范围与局限性