https://github.com/shijiawenwen/judgedeceiver
Universal and Transferable Adversarial Attacks on Aligned Language Models
Papers with Code 아카이브
Ingenuity
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Locomotion environment inspired by NASA’s Ingenuity helicopter.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/sj21j/Regularized_Relaxation
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/thompsonj/nanoGCG
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/thu-coai/safeunlearning
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/vinusankars/beast
Universal and Transferable Adversarial Attacks on Aligned Language Models
https://github.com/zhaoyiran924/probe-sampling
Universal and Transferable Adversarial Attacks on Aligned Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.