paper-with-me

Papers

A note on hyperparameters in black-box adversarial examples

2018-11-15 · Jamie Hayes

Since Biggio et al. (2013) and Szegedy et al. (2013) first drew attention to adversarial examples, there has been a flood of research into defending and attacking machine learning models. However, almost all proposed attacks assume white-box access to a model. In other words, the attacker is assumed to have perfect knowledge of the models weights and architecture. With this insider knowledge, a white-box attack can leverage gradient information to craft adversarial examples. Black-box attacks assume no knowledge of the model weights or architecture. These attacks craft adversarial examples using information only contained in the logits or hard classification label. Here, we assume the attacker can use the logits in order to find an adversarial example. Empirically, we show that 2-sided stochastic gradient estimation techniques are not sensitive to scaling parameters, and can be used to mount powerful black-box attacks requiring relatively few model queries.

📄 PDF Abstract BibTeX arXiv:1811.06539

Code (1)

jhayes14/black-box-attacks 공식 구현 tf

Similar Papers 제목 키워드 기반

Query-Efficient Black-box Adversarial Examples (superceded)

2017-12-19 · Andrew Ilyas, Logan Engstrom, Anish Athalye, Jessy Lin

Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box …

Adversarial Attack

Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization

2019-05-16 · Seungyong Moon, Gaon An, Hyun Oh Song

Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers. However, in the black-box setting, the attacker is limited on…

Combinatorial Optimization

Backpropagating Linearly Improves Transferability of Adversarial Examples

2020-12-07 · NeurIPS 2020 12 · Yiwen Guo, Qizhang Li, Hao Chen

The vulnerability of deep neural networks (DNNs) to adversarial examples has drawn great attention from the community. In this paper, we study the transferability of such examples, which lays the foundation of many black…

Detecting Adversarial Examples via Neural Fingerprinting

2018-03-11 · Sumanth Dathathri, Stephan Zheng, Tianwei Yin, Richard M. Murray 외

Deep neural networks are vulnerable to adversarial examples, which dramatically alter model output using small input changes. We propose Neural Fingerprinting, a simple, yet effective method to detect adversarial example…

Improving Adversarial Robustness via Attention and Adversarial Logit Pairing

2019-08-23 · Dou Goodman, Xingjian Li, Ji Liu, Dejing Dou 외

Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. In this paper, we develop…

Adversarial Robustness