arXiv:2407.09165
공식 코드 · Papers with Code
Robust Yet Efficient Conformal Prediction Sets
원문 초록
Conformal prediction (CP) can convert any model's output into prediction sets guaranteed to include the true label with any user-specified probability. However, same as the model itself, CP is vulnerable to adversarial test examples (evasion) and perturbed calibration data (poisoning). We derive provably robust sets by bounding the worst-case change in conformity scores. Our tighter bounds lead to more efficient sets. We cover both continuous and discrete (sparse) data and our guarantees work both for evasion and poisoning attacks (on both features and labels).
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability
Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks
Conformal Prediction for Zero-Shot Models
Optimal Conformal Prediction under Epistemic Uncertainty
Robust Vision-Based Runway Detection through Conformal Prediction and Conformal mAP
Privacy-Preserving Conformal Prediction Under Local Differential Privacy
토론
이 논문과 연결된 포럼 글이 아직 없습니다.