Defuse: Debugging Classifiers Through Distilling Unrestricted Adversarial Examples
With the greater proliferation of machine learning models, the imperative of diagnosing and correcting bugs in models has become increasingly clear. As a route to better discover and fix model bugs, we propose failure scenarios: regions on the data manifold that are incorrectly classified by a model. We propose an end-to-end debugging framework called Defuse to use these regions for fixing faulty classifier predictions. The Defuse framework works in three steps. First, Defuse identifies many unrestricted adversarial examples—naturally occurring instances that are misclassified—using a generative model. Next, the procedure distills the misclassified data using clustering. This step both reveals sources of model error and helps facilitate labeling. Last, the method corrects model behavior on the distilled scenarios through an optimization based approach. We illustrate the utility of our framework on a variety of image data sets. We find that Defuse identifies and resolves concerning predictions while maintaining model generalization.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringSimilar Papers 제목 키워드 기반
Defuse: Harnessing Unrestricted Adversarial Examples for Debugging Models Beyond Test Accuracy
We typically compute aggregate statistics on held-out test data to assess the generalization of machine learning models. However, statistics on test data often overstate model generalization, and thus, the performance of…
BIG-bench Machine LearningCodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model
Code Large Language Models (Code LLMs) have gained significant attention in the industry due to their wide applications in the full lifecycle of software engineering. However, the effectiveness of existing models in unde…
Code GenerationCode TranslationHumanEvalLanguage Modeling+2ColorFool: Semantic Adversarial Colorization
Adversarial attacks that generate small L_p-norm perturbations to mislead classifiers have limited success in black-box settings and with unseen classifiers. These attacks are also not robust to defenses that use denoisi…
Adversarial AttackColorizationDenoisingAdaptive Generation of Unrestricted Adversarial Inputs
Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some $l_p$ norm. Although studying these attacks is …
HILDIF: Interactive Debugging of NLI Models Using Influence Functions
Biases and artifacts in training data can cause unwelcome behavior in text classifiers (such as shallow pattern matching), leading to lack of generalizability. One solution to this problem is to include users in the loop…
Natural Language Inference