Recent improvements of ASR models in the face of adversarial attacks
- URL: http://arxiv.org/abs/2203.16536v1
- Date: Tue, 29 Mar 2022 22:40:37 GMT
- Title: Recent improvements of ASR models in the face of adversarial attacks
- Authors: Raphael Olivier, Bhiksha Raj
- Abstract summary: Speech Recognition models are vulnerable to adversarial attacks.
We show that the relative strengths of different attack algorithms vary considerably when changing the model architecture.
We release our source code as a package that should help future research in evaluating their attacks and defenses.
- Score: 28.934863462633636
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Like many other tasks involving neural networks, Speech Recognition models
are vulnerable to adversarial attacks. However recent research has pointed out
differences between attacks and defenses on ASR models compared to image
models. Improving the robustness of ASR models requires a paradigm shift from
evaluating attacks on one or a few models to a systemic approach in evaluation.
We lay the ground for such research by evaluating on various architectures a
representative set of adversarial attacks: targeted and untargeted,
optimization and speech processing-based, white-box, black-box and targeted
attacks. Our results show that the relative strengths of different attack
algorithms vary considerably when changing the model architecture, and that the
results of some attacks are not to be blindly trusted. They also indicate that
training choices such as self-supervised pretraining can significantly impact
robustness by enabling transferable perturbations. We release our source code
as a package that should help future research in evaluating their attacks and
defenses.
Related papers
- MirrorCheck: Efficient Adversarial Defense for Vision-Language Models [55.73581212134293]
We propose a novel, yet elegantly simple approach for detecting adversarial samples in Vision-Language Models.
Our method leverages Text-to-Image (T2I) models to generate images based on captions produced by target VLMs.
Empirical evaluations conducted on different datasets validate the efficacy of our approach.
arXiv Detail & Related papers (2024-06-13T15:55:04Z) - BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack [22.408968332454062]
We study the unique, less-well understood problem of generating sparse adversarial samples simply by observing the score-based replies to model queries.
We develop the BruSLeAttack-a new, faster (more query-efficient) algorithm for the problem.
Our work facilitates faster evaluation of model vulnerabilities and raises our vigilance on the safety, security and reliability of deployed systems.
arXiv Detail & Related papers (2024-04-08T08:59:26Z) - Deviations in Representations Induced by Adversarial Attacks [0.0]
Research has shown that deep learning models are vulnerable to adversarial attacks.
This finding brought about a new direction in research, whereby algorithms were developed to attack and defend vulnerable networks.
We present a method for measuring and analyzing the deviations in representations induced by adversarial attacks.
arXiv Detail & Related papers (2022-11-07T17:40:08Z) - A Closer Look at Evaluating the Bit-Flip Attack Against Deep Neural
Networks [0.0]
Bit-Flip Attack (BFA) aims at drastically dropping the performance of a model by targeting its parameters stored in memory.
This work is the first to present the impact of the BFA against fully-connected architectures.
arXiv Detail & Related papers (2022-09-28T17:04:39Z) - Membership-Doctor: Comprehensive Assessment of Membership Inference
Against Machine Learning Models [11.842337448801066]
We present a large-scale measurement of different membership inference attacks and defenses.
We find that some assumptions of the threat model, such as same-architecture and same-distribution between shadow and target models, are unnecessary.
We are also the first to execute attacks on the real-world data collected from the Internet, instead of laboratory datasets.
arXiv Detail & Related papers (2022-08-22T17:00:53Z) - Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial
Robustness [53.094682754683255]
We propose a Model-Agnostic Meta-Attack (MAMA) approach to discover stronger attack algorithms automatically.
Our method learns the in adversarial attacks parameterized by a recurrent neural network.
We develop a model-agnostic training algorithm to improve the ability of the learned when attacking unseen defenses.
arXiv Detail & Related papers (2021-10-13T13:54:24Z) - Adaptive Feature Alignment for Adversarial Training [56.17654691470554]
CNNs are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications.
We propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths.
Our method is trained to automatically align features of arbitrary attacking strength.
arXiv Detail & Related papers (2021-05-31T17:01:05Z) - Deep Image Destruction: A Comprehensive Study on Vulnerability of Deep
Image-to-Image Models against Adversarial Attacks [104.8737334237993]
We present comprehensive investigations into the vulnerability of deep image-to-image models to adversarial attacks.
For five popular image-to-image tasks, 16 deep models are analyzed from various standpoints.
We show that unlike in image classification tasks, the performance degradation on image-to-image tasks can largely differ depending on various factors.
arXiv Detail & Related papers (2021-04-30T14:20:33Z) - ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine
Learning Models [64.03398193325572]
Inference attacks against Machine Learning (ML) models allow adversaries to learn about training data, model parameters, etc.
We concentrate on four attacks - namely, membership inference, model inversion, attribute inference, and model stealing.
Our analysis relies on a modular re-usable software, ML-Doctor, which enables ML model owners to assess the risks of deploying their models.
arXiv Detail & Related papers (2021-02-04T11:35:13Z) - Learning to Attack: Towards Textual Adversarial Attacking in Real-world
Situations [81.82518920087175]
Adversarial attacking aims to fool deep neural networks with adversarial examples.
We propose a reinforcement learning based attack model, which can learn from attack history and launch attacks more efficiently.
arXiv Detail & Related papers (2020-09-19T09:12:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.