Improving LIME Robustness with Smarter Locality Sampling
Explainability algorithms such as LIME have enabled machine learning systems to adopt transparency and fairness, which are important qualities in commercial use cases. However, recent work has shown that LIME's naive sampling strategy can be exploited by an adversary to conceal biased, harmful behavior. We propose to make LIME more robust by training a generative adversarial network to sample more realistic synthetic data which the explainer uses to generate explanations. Our experiments demonstrate that our proposed method demonstrates an increase in accuracy across three real-world datasets in detecting biased, adversarial behavior compared to vanilla LIME. This is achieved while maintaining comparable explanation quality, with up to 99.94\% in top-1 accuracy in some cases.
Code (1)
Tasks
FairnessGenerative Adversarial NetworkMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
RoPE-LIME: RoPE-Space Locality + Sparse-K Sampling for Efficient LLM Attribution
Explaining closed-source Large Language Model (LLM) outputs is challenging because API access prevents gradient-based attribution, while perturbation methods are costly and noisy when they depend on regenerated text. We …
s-LIME: Reconciling Locality and Fidelity in Linear Explanations
The benefit of locality is one of the major premises of LIME, one of the most prominent methods to explain black-box machine learning models. This emphasis relies on the postulate that the more locally we look at the vic…
ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings
Explainable Artificial Intelligence (XAI) methods, such as Local Interpretable Model-Agnostic Explanations (LIME), have advanced the interpretability of black-box machine learning models by approximating their behavior l…
Contrastive LearningTransfer LearningOn Locality of Local Explanation Models
Shapley values provide model agnostic feature attributions for model outcome at a particular instance by simulating feature absence under a global population distribution. The use of a global population can lead to poten…
audioLIME: Listenable Explanations Using Source Separation
Deep neural networks (DNNs) are successfully applied in a wide variety of music information retrieval (MIR) tasks but their predictions are usually not interpretable. We propose audioLIME, a method based on Local Interpr…
Information RetrievalMusic Information RetrievalMusic TaggingRetrieval