The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples

• URL: http://arxiv.org/abs/2009.05487v3
• Date: Thu, 26 Aug 2021 08:40:29 GMT
• Title: The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples
• Authors: Timo Freiesleben
• Abstract summary: We argue that the relationship to the true label and the tolerance with respect to proximity are two properties that formally distinguish CEs and AEs. We show connections between current methods for generating CEs and AEs, and estimate that the fields will merge more and more as the number of common use-cases grows.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The same method that creates adversarial examples (AEs) to fool image-classifiers can be used to generate counterfactual explanations (CEs) that explain algorithmic decisions. This observation has led researchers to consider CEs as AEs by another name. We argue that the relationship to the true label and the tolerance with respect to proximity are two properties that formally distinguish CEs and AEs. Based on these arguments, we introduce CEs, AEs, and related concepts mathematically in a common framework. Furthermore, we show connections between current methods for generating CEs and AEs, and estimate that the fields will merge more and more as the number of common use-cases grows.

Related papers

• Rethinking Distance Metrics for Counterfactual Explainability [53.436414009687]
  We investigate a framing for counterfactual generation methods that considers counterfactuals not as independent draws from a region around the reference, but as jointly sampled with the reference from the underlying data distribution. We derive a distance metric, tailored for counterfactual similarity that can be applied to a broad range of settings.
  arXiv  Detail & Related papers  (2024-10-18T15:06:50Z)
• Applying Attribution Explanations in Truth-Discovery Quantitative Bipolar Argumentation Frameworks [18.505289553533164]
  Argument Attribution Explanations (AAEs) and Relation Attribution Explanations (RAEs) are used to explain the strength of arguments under gradual semantics. We apply AAEs and RAEs to Truth Discovery QBAFs, which assess the trustworthiness of sources and their claims. We find that both AAEs and RAEs can provide interesting explanations and can give non-trivial and surprising insights.
  arXiv  Detail & Related papers  (2024-09-09T17:36:39Z)
• CausalConceptTS: Causal Attributions for Time Series Classification using High Fidelity Diffusion Models [1.068128849363198]
  We introduce a novel framework to assess the causal effect of concepts on specific classification outcomes. We leverage state-of-the-art diffusion-based generative models to estimate counterfactual outcomes. Our approach compares these causal attributions with closely related associational attributions, both theoretically and empirically.
  arXiv  Detail & Related papers  (2024-05-24T18:33:18Z)
• Introducing User Feedback-based Counterfactual Explanations (UFCE) [49.1574468325115]
  Counterfactual explanations (CEs) have emerged as a viable solution for generating comprehensible explanations in XAI. UFCE allows for the inclusion of user constraints to determine the smallest modifications in the subset of actionable features. UFCE outperforms two well-known CE methods in terms of textitproximity, textitsparsity, and textitfeasibility.
  arXiv  Detail & Related papers  (2024-02-26T20:09:44Z)
• What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings [20.100378168629195]
  We provide a similarity flooding perspective to explain existing translation-based and aggregation-based EA models. We prove that the embedding learning process of these models actually seeks a fixpoint of pairwise similarities between entities.
  arXiv  Detail & Related papers  (2023-06-05T06:50:09Z)
• Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning [64.78972193105443]
  This paper presents a novel AE detection framework, named trustworthy for predictions. performs the detection by distinguishing the AE's abnormal relation with its augmented versions. An off-the-shelf Self-Supervised Learning (SSL) model is used to extract the representation and predict the label.
  arXiv  Detail & Related papers  (2022-08-31T08:18:44Z)
• Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings [70.390286614242]
  We propose a novel regularizer -- namely, DUality-induced RegulArizer (DURA) -- which effectively encourages the entities with similar semantics to have similar embeddings. Experiments demonstrate that DURA consistently and significantly improves the performance of state-of-the-art semantic matching models.
  arXiv  Detail & Related papers  (2022-03-24T09:24:39Z)
• Online Learning of Competitive Equilibria in Exchange Economies [94.24357018178867]
  In economics, the sharing of scarce resources among multiple rational agents is a classical problem. We propose an online learning mechanism to learn agent preferences. We demonstrate the effectiveness of this mechanism through numerical simulations.
  arXiv  Detail & Related papers  (2021-06-11T21:32:17Z)
• Influence-Driven Explanations for Bayesian Network Classifiers [16.708069984516964]
  We focus on explanations for discrete network Bayesian classifiers (BCs) We propose influence-driven explanations (IDXs) for BCs that include intermediate variables in explanations, rather than just the input and output variables as is standard practice.
  arXiv  Detail & Related papers  (2020-12-10T16:00:51Z)
• Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training [49.9995628166064]
  We propose CTEG, a model equipped with two mechanisms to learn to decouple easily-confused relations. On the one hand, an EGA mechanism is introduced to guide the attention to filter out information causing confusion. On the other hand, a Confusion-Aware Training (CAT) method is proposed to explicitly learn to distinguish relations.
  arXiv  Detail & Related papers  (2020-10-21T11:07:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.