SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.18942 · NeurIPS · 2024

Verifiably Robust Conformal Prediction

Linus Jeary, Tom Kuipers, Mehran Hosseini, Nicola Paoletti

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
ddv-lab/Verifiably_Robust_CP — 8 of 10
FunctionStatusWhere it lives
calculate_Bern_bound Ran ddv-lab/Verifiably_Robust_CP/VRCP_Classification/VRCP/experiment.py
pointer only (licence: NONE) · get_code("eee0fffccb507d98")
calibration Ran ddv-lab/Verifiably_Robust_CP/VRCP_Classification/VRCP/experiment.py
pointer only (licence: NONE) · get_code("0f6a278ae3d77fa8")
class_probability_score Ran ddv-lab/Verifiably_Robust_CP/VRCP_Classification/VRCP/experiment.py
pointer only (licence: NONE) · get_code("b19e659788c63b74")
evaluate_predictions Ran ddv-lab/Verifiably_Robust_CP/VRCP_Classification/VRCP/experiment.py
pointer only (licence: NONE) · get_code("03cd6687b1d4c3be")
get_scores Ran ddv-lab/Verifiably_Robust_CP/VRCP_Classification/VRCP/experiment.py
pointer only (licence: NONE) · get_code("f780342ea9e8fa2e")
prediction Ran ddv-lab/Verifiably_Robust_CP/VRCP_Classification/VRCP/experiment.py
pointer only (licence: NONE) · get_code("5351b0a2e6494ed5")
ranking_score Ran ddv-lab/Verifiably_Robust_CP/VRCP_Classification/VRCP/experiment.py
pointer only (licence: NONE) · get_code("532b67a2aa47c799")
sigmoid_score Ran ddv-lab/Verifiably_Robust_CP/VRCP_Classification/VRCP/experiment.py
pointer only (licence: NONE) · get_code("d7ed63bdfb4157ae")
_build_scores_list Not yet run ddv-lab/Verifiably_Robust_CP/VRCP_Classification/VRCP/experiment.py
pointer only (licence: NONE) · get_code("3925f3d4836f8634")
run_experiments Not yet run ddv-lab/Verifiably_Robust_CP/VRCP_Classification/VRCP/experiment.py
pointer only (licence: NONE) · get_code("9661e07d6afe5eec")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Conformal Prediction (CP) is a popular uncertainty quantification method that provides distribution-free, statistically valid prediction sets, assuming that training and test data are exchangeable. In such a case, CP's prediction sets are guaranteed to cover the (unknown) true test output with a user-specified probability. Nevertheless, this guarantee is violated when the data is subjected to adversarial attacks, which often result in a significant loss of coverage. Recently, several approaches have been put forward to recover CP guarantees in this setting. These approaches leverage variations of randomised smoothing to produce conservative sets which account for the effect of the adversarial perturbations. They are, however, limited in that they only support ℓ 2 -bounded perturbations and classification tasks. This paper introduces VRCP (Verifiably Robust Conformal Prediction), a new framework that leverages recent neural network verification methods to recover coverage guarantees under adversarial attacks. Our VRCP method is the first to support perturbations bounded by arbitrary norms including ℓ 1 , ℓ 2 , and ℓ ∞ , as well as regression tasks. We evaluate and compare our approach on image classification tasks (CIFAR10, CIFAR100, and TinyImageNet) and regression tasks for deep reinforcement learning environments. In every case, VRCP achieves above nominal coverage and yields significantly more efficient and informative prediction regions than the SotA.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2405.18942")
get_code_for_paper("2405.18942")
have("2405.18942")

Connect an agent — have() is free.