ترغب بنشر مسار تعليمي؟ اضغط هنا

Detecting Trojaned DNNs Using Counterfactual Attributions

251   0   0.0 ( 0 )
 نشر من قبل Susmit Jha
 تاريخ النشر 2020
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

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 the 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.



قيم البحث

اقرأ أيضاً

87 - Xin Wang , Shuyun Lin , Hao Zhang 2021
This paper aims to explain adversarial attacks in terms of how adversarial perturbations contribute to the attacking task. We estimate attributions of different image regions to the decrease of the attacking cost based on the Shapley value. We define and quantify interactions among adversarial perturbation pixels, and decompose the entire perturbation map into relatively independent perturbation components. The decomposition of the perturbation map shows that adversarially-trained DNNs have more perturbation components in the foreground than normally-trained DNNs. Moreover, compared to the normally-trained DNN, the adversarially-trained DNN have more components which mainly decrease the score of the true category. Above analyses provide new insights into the understanding of adversarial attacks.
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.
This paper aims to explain deep neural networks (DNNs) from the perspective of multivariate interactions. In this paper, we define and quantify the significance of interactions among multiple input variables of the DNN. Input variables with strong in teractions usually form a coalition and reflect prototype features, which are memorized and used by the DNN for inference. We define the significance of interactions based on the Shapley value, which is designed to assign the attribution value of each input variable to the inference. We have conducted experiments with various DNNs. Experimental results have demonstrated the effectiveness of the proposed method.
89 - Yash Goyal , Ziyan Wu , Jan Ernst 2019
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.
In this work, we propose an introspection technique for deep neural networks that relies on a generative model to instigate salient editing of the input image for model interpretation. Such modification provides the fundamental interventional operati on that allows us to obtain answers to counterfactual inquiries, i.e., what meaningful change can be made to the input image in order to alter the prediction. We demonstrate how to reveal interesting properties of the given classifiers by utilizing the proposed introspection approach on both the MNIST and the CelebA dataset.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا