paper-with-me

Papers

Interpreting Attributions and Interactions of Adversarial Attacks

2021-08-16 · ICCV 2021 10 · Xin Wang, Shuyun Lin, Hao Zhang, Yufei Zhu, Quanshi Zhang

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.

📄 PDF Abstract BibTeX arXiv:2108.06895

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Interpreting and improving deep-learning models with reality checks

2021-08-16 · Chandan Singh, Wooseok Ha, Bin Yu

Recent deep-learning models have achieved impressive predictive performance by learning complex functions of many variables, often at the cost of interpretability. This chapter covers recent work aiming to interpret mode…

Deep Learning

Attributions All the Way Down? The Metagame of Interpretability

2026-05-07 · Hubert Baniecki, Przemyslaw Biecek, Fabian Fumagalli arxiv

We introduce the metagame, a conceptual framework for quantifying second-order interaction effects of model explanations. For any first-order attribution $φ(f)$ explaining a model $f$, we measure the directional influenc…

Influence-based Attributions can be Manipulated

2024-09-08 · Chhavi Yadav, Ruihan Wu, Kamalika Chaudhuri

Influence Functions are a standard tool for attributing predictions to training data in a principled manner and are widely used in applications such as data valuation and fairness. In this work, we present realistic ince…

Data ValuationFairness

Did the Model Understand the Question?

2018-05-14 · ACL 2018 7 · Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan, Kedar Dhamdhere

We analyze state-of-the-art deep learning models for three tasks: question answering on (1) images, (2) tables, and (3) passages of text. Using the notion of \emph{attribution} (word importance), we find that these deep …

modelQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

ML-LOO: Detecting Adversarial Examples with Feature Attribution

2019-06-08 · Puyudi Yang, Jianbo Chen, Cho-Jui Hsieh, Jane-Ling Wang 외

Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image d…