DeltaBound Attack: Efficient decision-based attack in low queries regime

10/01/2022
by   Lorenzo Rossi, et al.
0

Deep neural networks and other machine learning systems, despite being extremely powerful and able to make predictions with high accuracy, are vulnerable to adversarial attacks. We proposed the DeltaBound attack: a novel, powerful attack in the hard-label setting with ℓ_2 norm bounded perturbations. In this scenario, the attacker has only access to the top-1 predicted label of the model and can be therefore applied to real-world settings such as remote API. This is a complex problem since the attacker has very little information about the model. Consequently, most of the other techniques present in the literature require a massive amount of queries for attacking a single example. Oppositely, this work mainly focuses on the evaluation of attack's power in the low queries regime ≤ 1000 queries) with ℓ_2 norm in the hard-label settings. We find that the DeltaBound attack performs as well and sometimes better than current state-of-the-art attacks while remaining competitive across different kinds of models. Moreover, we evaluate our method against not only deep neural networks, but also non-deep learning models, such as Gradient Boosting Decision Trees and Multinomial Naive Bayes.

READ FULL TEXT

page 5

page 8

page 13

page 14

research
06/23/2020

RayS: A Ray Searching Method for Hard-label Adversarial Attack

Deep neural networks are vulnerable to adversarial attacks. Among differ...
research
07/12/2018

Query-Efficient Hard-label Black-box Attack:An Optimization-based Approach

We study the problem of attacking a machine learning model in the hard-l...
research
02/04/2021

PredCoin: Defense against Query-based Hard-label Attack

Many adversarial attacks and defenses have recently been proposed for De...
research
02/17/2020

Query-Efficient Physical Hard-Label Attacks on Deep Learning Visual Classification

We present Survival-OPT, a physical adversarial example algorithm in the...
research
07/26/2022

Generative Extraction of Audio Classifiers for Speaker Identification

It is perhaps no longer surprising that machine learning models, especia...
research
11/06/2017

Adversarial Frontier Stitching for Remote Neural Network Watermarking

The state of the art performance of deep learning models comes at a high...
research
10/22/2020

On the Power of Deep but Naive Partial Label Learning

Partial label learning (PLL) is a class of weakly supervised learning wh...

Please sign up or login with your details

Forgot password? Click here to reset