SNEAK: Synonymous Sentences-Aware Adversarial Attack on Natural Language Video Localization

12/08/2021
by   Wenbo Gou, et al.
0

Natural language video localization (NLVL) is an important task in the vision-language understanding area, which calls for an in-depth understanding of not only computer vision and natural language side alone, but more importantly the interplay between both sides. Adversarial vulnerability has been well-recognized as a critical security issue of deep neural network models, which requires prudent investigation. Despite its extensive yet separated studies in video and language tasks, current understanding of the adversarial robustness in vision-language joint tasks like NLVL is less developed. This paper therefore aims to comprehensively investigate the adversarial robustness of NLVL models by examining three facets of vulnerabilities from both attack and defense aspects. To achieve the attack goal, we propose a new adversarial attack paradigm called synonymous sentences-aware adversarial attack on NLVL (SNEAK), which captures the cross-modality interplay between the vision and language sides.

READ FULL TEXT

page 2

page 7

research
06/19/2022

Towards Adversarial Attack on Vision-Language Pre-training Models

While vision-language pre-training model (VLP) has shown revolutionary i...
research
09/05/2018

Localizing Moments in Video with Temporal Language

Localizing moments in a longer video via natural language queries is a n...
research
02/10/2022

Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarios

Visual detection is a key task in autonomous driving, and it serves as o...
research
05/18/2023

Towards an Accurate and Secure Detector against Adversarial Perturbations

The vulnerability of deep neural networks to adversarial perturbations h...
research
06/13/2021

Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Models

Despite significant improvements in natural language understanding model...
research
01/20/2022

A Computational Model for Machine Thinking

A machine thinking model is proposed in this report based on recent adva...
research
06/21/2022

Why Robust Natural Language Understanding is a Challenge

With the proliferation of Deep Machine Learning into real-life applicati...

Please sign up or login with your details

Forgot password? Click here to reset