Introducing Adaptive Continuous Adversarial Training (ACAT) to Enhance ML Robustness

• URL: http://arxiv.org/abs/2403.10461v2
• Date: Wed, 29 May 2024 14:23:35 GMT
• Title: Introducing Adaptive Continuous Adversarial Training (ACAT) to Enhance ML Robustness
• Authors: Mohamed elShehaby, Aditya Kotha, Ashraf Matrawy,
• Abstract summary: ACAT integrates adversarial training samples into the model during continuous learning sessions. The accuracy of the under-attack ML-based SPAM filter increased from 69% to over 88% after just three retraining sessions.
• Score: 1.474723404975345
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adversarial training enhances the robustness of Machine Learning (ML) models against adversarial attacks. However, obtaining labeled training and adversarial training data in network/cybersecurity domains is challenging and costly. Therefore, this letter introduces Adaptive Continuous Adversarial Training (ACAT), a method that integrates adversarial training samples into the model during continuous learning sessions using real-world detected adversarial data. Experimental results with a SPAM detection dataset demonstrate that ACAT reduces the time required for adversarial sample detection compared to traditional processes. Moreover, the accuracy of the under-attack ML-based SPAM filter increased from 69% to over 88% after just three retraining sessions.

Related papers

• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization [36.10642858867033]
  Adversarial training is one of the best-performing methods in improving the robustness of deep language models. We introduce a novel, effective procedure for instead adversarial training with only clean data. Our approach requires zero adversarial samples for training and reduces time consumption by up to 70% compared to current best-performing adversarial training methods.
  arXiv  Detail & Related papers  (2023-06-27T02:46:08Z)
• CAT:Collaborative Adversarial Training [80.55910008355505]
  We propose a collaborative adversarial training framework to improve the robustness of neural networks. Specifically, we use different adversarial training methods to train robust models and let models interact with their knowledge during the training process. Cat achieves state-of-the-art adversarial robustness without using any additional data on CIFAR-10 under the Auto-Attack benchmark.
  arXiv  Detail & Related papers  (2023-03-27T05:37:43Z)
• GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks [73.88590165742721]
  We propose a novel adversarial training technique that exploits auxiliary tasks under a limited set of training data. Our approach extends single-task models into multi-task models during the min-max optimization of adversarial training. We demonstrate that guided multi-task learning is an actionable and promising avenue to push further the boundaries of model robustness.
  arXiv  Detail & Related papers  (2023-02-06T16:23:24Z)
• DAD: Data-free Adversarial Defense at Test Time [21.741026088202126]
  Deep models are highly susceptible to adversarial attacks. Privacy has become an important concern, restricting access to only trained models but not the training data. We propose a completely novel problem of 'test-time adversarial defense in absence of training data and even their statistics'
  arXiv  Detail & Related papers  (2022-04-04T15:16:13Z)
• Adaptive perturbation adversarial training: based on reinforcement learning [9.563820241076103]
  One of the shortcomings of adversarial training is that it will reduce the recognition accuracy of normal samples. Adaptive adversarial training is proposed to alleviate this problem. It uses marginal adversarial samples that are close to the decision boundary but does not cross the decision boundary for adversarial training.
  arXiv  Detail & Related papers  (2021-08-30T13:49:55Z)
• Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks [10.058068783476598]
  This paper proposed a meta-learning method on the adversarially robust neural network called Long-term Cross Adversarial Training (LCAT) Due to cross-adversarial training, LCAT only needs half of the adversarial training epoch than AQ, resulting in a low adversarial training epoch. Experiment results show that LCAT achieves superior performance both on the clean and adversarial few-shot classification accuracy.
  arXiv  Detail & Related papers  (2021-06-22T06:31:16Z)
• Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training [55.824641135682725]
  Domain adaptation experiments using WSJ as a source domain and TED-LIUM 3 as well as SWITCHBOARD show that up to 80% of the performance of a system trained on ground-truth data can be recovered.
  arXiv  Detail & Related papers  (2020-11-26T18:51:26Z)
• Adversarial Self-Supervised Contrastive Learning [62.17538130778111]
  Existing adversarial learning approaches mostly use class labels to generate adversarial samples that lead to incorrect predictions. We propose a novel adversarial attack for unlabeled data, which makes the model confuse the instance-level identities of the perturbed data samples. We present a self-supervised contrastive learning framework to adversarially train a robust neural network without labeled data.
  arXiv  Detail & Related papers  (2020-06-13T08:24:33Z)
• Efficient Adversarial Training with Transferable Adversarial Examples [58.62766224452761]
  We show that there is high transferability between models from neighboring epochs in the same training process. We propose a novel method, Adversarial Training with Transferable Adversarial Examples (ATTA) that can enhance the robustness of trained models.
  arXiv  Detail & Related papers  (2019-12-27T03:05:05Z)

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.