DeepAI AI Chat
Log In Sign Up

Adversarial Imitation Attack

03/28/2020
by   Mingyi Zhou, et al.
University of Electronic Science and Technology of China
53

Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate adversarial examples and their attack success rates heavily rely on the transferability of adversarial examples. Current score-based and decision-based attacks require lots of queries for the attacked models. In this study, we propose a novel adversarial imitation attack. First, it produces a replica of the attacked model by a two-player game like the generative adversarial networks (GANs). The objective of the generative model is to generate examples that lead the imitation model returning different outputs with the attacked model. The objective of the imitation model is to output the same labels with the attacked model under the same inputs. Then, the adversarial examples generated by the imitation model are utilized to fool the attacked model. Compared with the current substitute attacks, imitation attacks can use less training data to produce a replica of the attacked model and improve the transferability of adversarial examples. Experiments demonstrate that our imitation attack requires less training data than the black-box substitute attacks, but achieves an attack success rate close to the white-box attack on unseen data with no query.

READ FULL TEXT

page 13

page 14

page 15

01/08/2018

Generating adversarial examples with adversarial networks

Deep neural networks (DNNs) have been found to be vulnerable to adversar...
03/28/2020

DaST: Data-free Substitute Training for Adversarial Attacks

Machine learning models are vulnerable to adversarial examples. For the ...
04/30/2020

Imitation Attacks and Defenses for Black-box Machine Translation Systems

We consider an adversary looking to steal or attack a black-box machine ...
03/06/2023

On the Feasibility of Specialized Ability Extracting for Large Language Code Models

Recent progress in large language code models (LLCMs) has led to a drama...
08/03/2021

DeepFreeze: Cold Boot Attacks and High Fidelity Model Recovery on Commercial EdgeML Device

EdgeML accelerators like Intel Neural Compute Stick 2 (NCS) can enable e...
08/05/2021

BOSS: Bidirectional One-Shot Synthesis of Adversarial Examples

The design of additive imperceptible perturbations to the inputs of deep...
11/23/2022

Adversarial Attacks are a Surprisingly Strong Baseline for Poisoning Few-Shot Meta-Learners

This paper examines the robustness of deployed few-shot meta-learning sy...