Towards Efficient Transferable Preemptive Adversarial Defense
- URL: http://arxiv.org/abs/2407.15524v1
- Date: Mon, 22 Jul 2024 10:23:44 GMT
- Title: Towards Efficient Transferable Preemptive Adversarial Defense
- Authors: Hanrui Wang, Ching-Chun Chang, Chun-Shien Lu, Isao Echizen,
- Abstract summary: Deep learning technology has become untrustworthy because of its sensitivity to perturbations.
We have devised a strategy for "attacking" the message before it is attacked.
With the running of only three steps, our Fast Preemption framework outperforms benchmark training-time, test-time, and preemptive adversarial defenses.
- Score: 13.252842556505174
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Deep learning technology has brought convenience and advanced developments but has become untrustworthy because of its sensitivity to inconspicuous perturbations (i.e., adversarial attacks). Attackers utilize this sensitivity to slightly manipulate transmitted messages. To defend against such attacks, we have devised a strategy for "attacking" the message before it is attacked. This strategy, dubbed Fast Preemption, provides an efficient transferable preemptive defense by using different models for labeling inputs and learning crucial features. A forward-backward cascade learning algorithm is used to compute protective perturbations, starting with forward propagation optimization to achieve rapid convergence, followed by iterative backward propagation learning to alleviate overfitting. This strategy offers state-of-the-art transferability and protection across various systems. With the running of only three steps, our Fast Preemption framework outperforms benchmark training-time, test-time, and preemptive adversarial defenses. We have also devised the first to our knowledge effective white-box adaptive reversion attack and demonstrate that the protection added by our defense strategy is irreversible unless the backbone model, algorithm, and settings are fully compromised. This work provides a new direction to developing active defenses against adversarial attacks.
Related papers
- SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks [53.28390057407576]
Modern NLP models are often trained on public datasets drawn from diverse sources.
Data poisoning attacks can manipulate the model's behavior in ways engineered by the attacker.
Several strategies have been proposed to mitigate the risks associated with backdoor attacks.
arXiv Detail & Related papers (2024-05-19T14:50:09Z) - MPAT: Building Robust Deep Neural Networks against Textual Adversarial
Attacks [4.208423642716679]
We propose a malicious perturbation based adversarial training method (MPAT) for building robust deep neural networks against adversarial attacks.
Specifically, we construct a multi-level malicious example generation strategy to generate adversarial examples with malicious perturbations.
We employ a novel training objective function to ensure achieving the defense goal without compromising the performance on the original task.
arXiv Detail & Related papers (2024-02-29T01:49:18Z) - Mutual-modality Adversarial Attack with Semantic Perturbation [81.66172089175346]
We propose a novel approach that generates adversarial attacks in a mutual-modality optimization scheme.
Our approach outperforms state-of-the-art attack methods and can be readily deployed as a plug-and-play solution.
arXiv Detail & Related papers (2023-12-20T05:06:01Z) - Continual Adversarial Defense [38.77563936937233]
We propose the first continual adversarial defense framework that adapts to any attacks in a dynamic scenario.
In practice, CAD is modeled under four principles: (1) continual adaptation to new attacks without catastrophic forgetting, (2) few-shot adaptation, (3) memory-efficient adaptation, and (4) high accuracy on both clean and adversarial images.
arXiv Detail & Related papers (2023-12-15T01:38:26Z) - Guidance Through Surrogate: Towards a Generic Diagnostic Attack [101.36906370355435]
We develop a guided mechanism to avoid local minima during attack optimization, leading to a novel attack dubbed Guided Projected Gradient Attack (G-PGA)
Our modified attack does not require random restarts, large number of attack iterations or search for an optimal step-size.
More than an effective attack, G-PGA can be used as a diagnostic tool to reveal elusive robustness due to gradient masking in adversarial defenses.
arXiv Detail & Related papers (2022-12-30T18:45:23Z) - Projective Ranking-based GNN Evasion Attacks [52.85890533994233]
Graph neural networks (GNNs) offer promising learning methods for graph-related tasks.
GNNs are at risk of adversarial attacks.
arXiv Detail & Related papers (2022-02-25T21:52:09Z) - 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) - Mitigating Gradient-based Adversarial Attacks via Denoising and
Compression [7.305019142196582]
Gradient-based adversarial attacks on deep neural networks pose a serious threat.
They can be deployed by adding imperceptible perturbations to the test data of any network.
Denoising and dimensionality reduction are two distinct methods that have been investigated to combat such attacks.
arXiv Detail & Related papers (2021-04-03T22:57:01Z) - Guided Adversarial Attack for Evaluating and Enhancing Adversarial
Defenses [59.58128343334556]
We introduce a relaxation term to the standard loss, that finds more suitable gradient-directions, increases attack efficacy and leads to more efficient adversarial training.
We propose Guided Adversarial Margin Attack (GAMA), which utilizes function mapping of the clean image to guide the generation of adversaries.
We also propose Guided Adversarial Training (GAT), which achieves state-of-the-art performance amongst single-step defenses.
arXiv Detail & Related papers (2020-11-30T16:39:39Z)
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.