Jailbreaking ati Red-Teaming adanwo

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

1. Kini ibi-afẹde akọkọ ti itusilẹ jailbreak kan?
   • Lati gba awoṣe lati fori awọn ofin aabo ti a ṣe sinu rẹ
   • Lati titẹ soke awọn awoṣe ká esi akoko
   • Lati tumọ ọrọ si ede miiran
   • Lati dinku iye owo ti nṣiṣẹ awoṣe
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. Kilode ti awọn jailbreaks-shot pupọ ṣiṣẹ dara julọ bi awọn window ọrọ ti n gun?
   • Awọn itara gigun jẹ din owo lati ṣiṣẹ
   • Itọkasi to gun mu ki classifier ailewu ṣiṣẹ laifọwọyi
   • Awoṣe naa le ni ikun omi pẹlu ọpọlọpọ awọn apẹẹrẹ ifaramọ iro ti o yi ihuwasi rẹ pada
   • Awoṣe gbagbe awọn ilana atilẹba rẹ lẹhin awọn ọrọ 100
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. What should a red-team report include to make findings interpretable?
   • Only one successful prompt without context
   • A claim that all models fail identically
   • The model’s hidden training data
   • The tested model and version, prompt conditions, evaluation scope and limitations