paper-with-me

Papers

Adversarial Attacks on the Interpretation of Neuron Activation Maximization

2023-06-12 · Geraldin Nanfack, Alexander Fulleringer, Jonathan Marty, Michael Eickenberg, Eugene Belilovsky

The internal functional behavior of trained Deep Neural Networks is notoriously difficult to interpret. Activation-maximization approaches are one set of techniques used to interpret and analyze trained deep-learning models. These consist in finding inputs that maximally activate a given neuron or feature map. These inputs can be selected from a data set or obtained by optimization. However, interpretability methods may be subject to being deceived. In this work, we consider the concept of an adversary manipulating a model for the purpose of deceiving the interpretation. We propose an optimization framework for performing this manipulation and demonstrate a number of ways that popular activation-maximization interpretation techniques associated with CNNs can be manipulated to change the interpretations, shedding light on the reliability of these methods.

📄 PDF Abstract BibTeX arXiv:2306.07397

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Representation Understanding via Activation Maximization

2025-08-10 · Hongbo Zhu, Angelo Cangelosi arxiv

Understanding internal feature representations of deep neural networks (DNNs) is a fundamental step toward model interpretability. Inspired by neuroscience methods that probe biological neurons using visual stimuli, rece…

Bounded Adversarial Attack on Deep Content Features

2022-01-01 · CVPR 2022 1 · QiuLing Xu, Guanhong Tao, Xiangyu Zhang

We propose a novel adversarial attack targeting content features in some deep layer, that is, individual neurons in the layer. A naive method that enforces a fixed value/percentage bound for neuron activation values …

Adversarial Attack

Real-time Detection of Practical Universal Adversarial Perturbations

2021-05-16 · Kenneth T. Co, Luis Muñoz-González, Leslie Kanthan, Emil C. Lupu

Universal Adversarial Perturbations (UAPs) are a prominent class of adversarial examples that exploit the systemic vulnerabilities and enable physically realizable and robust attacks against Deep Neural Networks (DNNs). …

Blockingimage-classificationImage Classificationobject-detection+1

TRM-UAP: Enhancing the Transferability of Data-Free Universal Adversarial Perturbation via Truncated Ratio Maximization

2023-01-01 · ICCV 2023 1 · Yiran Liu, Xin Feng, Yunlong Wang, Wu Yang 외

Aiming at crafting a single universal adversarial perturbation (UAP) to fool CNN models for various data samples, universal attack enables a more efficient and accurate evaluation for the robustness of CNN models. Ea…

Interpreting Adversarial Examples by Activation Promotion and Suppression

2019-04-03 · Kaidi Xu, Sijia Liu, Gaoyuan Zhang, Mengshu Sun 외

It is widely known that convolutional neural networks (CNNs) are vulnerable to adversarial examples: images with imperceptible perturbations crafted to fool classifiers. However, interpretability of these perturbations i…

Adversarial Robustness