اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدFeature Attributions and Counterfactual Explanations Can Be Manipulated
153
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
As machine learning models are increasingly used in critical decision-making settings (e.g., healthcare, finance), there has been a growing emphasis on developing methods to explain model predictions. Such textit{explanations} are used to understand and establish trust in models and are vital components in machine learning pipelines. Though explanations are a critical piece in these systems, there is little understanding about how they are vulnerable to manipulation by adversaries. In this paper, we discuss how two broad classes of explanations are vulnerable to manipulation. We demonstrate how adversaries can design biased models that manipulate model agnostic feature attribution methods (e.g., LIME & SHAP) and counterfactual explanations that hill-climb during the counterfactual search (e.g., Wachters Algorithm & DiCE) into textit{concealing} the models biases. These vulnerabilities allow an adversary to deploy a biased model, yet explanations will not reveal this bias, thereby deceiving stakeholders into trusting the model. We evaluate the manipulations on real world data sets, including COMPAS and Communities & Crime, and find explanations can be manipulated in practice.
قيم البحث
اقرأ أيضاً
Counterfactual explanations are emerging as an attractive option for providing recourse to individuals adversely impacted by algorithmic decisions. As they are deployed in critical applications (e.g. law enforcement, financial lending), it becomes im
portant to ensure that we clearly understand the vulnerabilities of these methods and find ways to address them. However, there is little understanding of the vulnerabilities and shortcomings of counterfactual explanations. In this work, we introduce the first framework that describes the vulnerabilities of counterfactual explanations and shows how they can be manipulated. More specifically, we show counterfactual explanations may converge to drastically different counterfactuals under a small perturbation indicating they are not robust. Leveraging this insight, we introduce a novel objective to train seemingly fair models where counterfactual explanations find much lower cost recourse under a slight perturbation. We describe how these models can unfairly provide low-cost recourse for specific subgroups in the data while appearing fair to auditors. We perform experiments on loan and violent crime prediction data sets where certain subgroups achieve up to 20x lower cost recourse under the perturbation. These results raise concerns regarding the dependability of current counterfactual explanation techniques, which we hope will inspire investigations in robust counterfactual explanations.
We target the problem of detecting Trojans or backdoors in DNNs. Such models behave normally with typical inputs but produce specific incorrect predictions for inputs poisoned with a Trojan trigger. Our approach is based on a novel observation that t
he trigger behavior depends on a few ghost neurons that activate on trigger pattern and exhibit abnormally higher relative attribution for wrong decisions when activated. Further, these trigger neurons are also active on normal inputs of the target class. Thus, we use counterfactual attributions to localize these ghost neurons from clean inputs and then incrementally excite them to observe changes in the models accuracy. We use this information for Trojan detection by using a deep set encoder that enables invariance to the number of model classes, architecture, etc. Our approach is implemented in the TrinityAI tool that exploits the synergies between trustworthiness, resilience, and interpretability challenges in deep learning. We evaluate our approach on benchmarks with high diversity in model architectures, triggers, etc. We show consistent gains (+10%) over state-of-the-art methods that rely on the susceptibility of the DNN to specific adversarial attacks, which in turn requires strong assumptions on the nature of the Trojan attack.
In this work, we develop a technique to produce counterfactual visual explanations. Given a query image $I$ for which a vision system predicts class $c$, a counterfactual visual explanation identifies how $I$ could change such that the system would o
utput a different specified class $c$. To do this, we select a distractor image $I$ that the system predicts as class $c$ and identify spatial regions in $I$ and $I$ such that replacing the identified region in $I$ with the identified region in $I$ would push the system towards classifying $I$ as $c$. We apply our approach to multiple image classification datasets generating qualitative results showcasing the interpretability and discriminativeness of our counterfactual explanations. To explore the effectiveness of our explanations in teaching humans, we present machine teaching experiments for the task of fine-grained bird classification. We find that users trained to distinguish bird species fare better when given access to counterfactual explanations in addition to training examples.
We prove two complexity results about the H-index concerned with the Google scholar merge operation on ones scientific articles. The results show that, although it is hard to merge ones articles in an optimal way, it is easy to merge them in such a w
ay that ones H-index increases. This suggests the need for an alternative scientific performance measure that is resistant to this type of manipulation.
Feature attributions and counterfactual explanations are popular approaches to explain a ML model. The former assigns an importance score to each input feature, while the latter provides input examples with minimal changes to alter the models predict
ions. To unify these approaches, we provide an interpretation based on the actual causality framework and present two key results in terms of their use. First, we present a method to generate feature attribution explanations from a set of counterfactual examples. These feature attributions convey how important a feature is to changing the classification outcome of a model, especially on whether a subset of features is necessary and/or sufficient for that change, which attribution-based methods are unable to provide. Second, we show how counterfactual examples can be used to evaluate the goodness of an attribution-based explanation in terms of its necessity and sufficiency. As a result, we highlight the complementarity of these two approaches. Our evaluation on three benchmark datasets - Adult-Income, LendingClub, and German-Credit - confirms the complementarity. Feature attribution methods like LIME and SHAP and counterfactual explanation methods like Wachter et al. and DiCE often do not agree on feature importance rankings. In addition, by restricting the features that can be modified for generating counterfactual examples, we find that the top-k features from LIME or SHAP are often neither necessary nor sufficient explanations of a models prediction. Finally, we present a case study of different explanation methods on a real-world hospital triage problem
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
