Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search

• URL: http://arxiv.org/abs/2405.06073v1
• Date: Thu, 9 May 2024 19:55:07 GMT
• Title: Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search
• Authors: Zachary Coalson, Huazheng Wang, Qingyun Wu, Sanghyun Hong,
• Abstract summary: We present a data poisoning attack, when injected to the training data used for architecture search. We first define the attack objective for crafting poisoning samples that can induce the victim to generate sub-optimal architectures. We present techniques that the attacker can use to significantly reduce the computational costs of crafting poisoning samples.
• Score: 20.258148613490132
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we study the robustness of "data-centric" approaches to finding neural network architectures (known as neural architecture search) to data distribution shifts. To audit this robustness, we present a data poisoning attack, when injected to the training data used for architecture search that can prevent the victim algorithm from finding an architecture with optimal accuracy. We first define the attack objective for crafting poisoning samples that can induce the victim to generate sub-optimal architectures. To this end, we weaponize existing search algorithms to generate adversarial architectures that serve as our objectives. We also present techniques that the attacker can use to significantly reduce the computational costs of crafting poisoning samples. In an extensive evaluation of our poisoning attack on a representative architecture search algorithm, we show its surprising robustness. Because our attack employs clean-label poisoning, we also evaluate its robustness against label noise. We find that random label-flipping is more effective in generating sub-optimal architectures than our clean-label attack. Our results suggests that care must be taken for the data this emerging approach uses, and future work is needed to develop robust algorithms.

Related papers

• Have You Poisoned My Data? Defending Neural Networks against Data Poisoning [0.393259574660092]
  We propose a novel approach to detect and filter poisoned datapoints in the transfer learning setting. We show that effective poisons can be successfully differentiated from clean points in the characteristic vector space. Our evaluation shows that our proposal outperforms existing approaches in defense rate and final trained model performance.
  arXiv  Detail & Related papers  (2024-03-20T11:50:16Z)
• A Discrepancy Aware Framework for Robust Anomaly Detection [51.710249807397695]
  We present a Discrepancy Aware Framework (DAF), which demonstrates robust performance consistently with simple and cheap strategies. Our method leverages an appearance-agnostic cue to guide the decoder in identifying defects, thereby alleviating its reliance on synthetic appearance. Under the simple synthesis strategies, it outperforms existing methods by a large margin. Furthermore, it also achieves the state-of-the-art localization performance.
  arXiv  Detail & Related papers  (2023-10-11T15:21:40Z)
• Neural Architecture Design and Robustness: A Dataset [11.83842808044211]
  We introduce a database on neural architecture design and robustness evaluations. We evaluate all these networks on a range of common adversarial attacks and corruption types. We find that carefully crafting the topology of a network can have substantial impact on its robustness.
  arXiv  Detail & Related papers  (2023-06-11T16:02:14Z)
• Differentiable Search of Accurate and Robust Architectures [22.435774101990752]
  adversarial training has been drawing increasing attention because of its simplicity and effectiveness. Deep neural networks (DNNs) are found to be vulnerable to adversarial attacks. We propose DSARA to automatically search for the neural architectures that are accurate and robust after adversarial training.
  arXiv  Detail & Related papers  (2022-12-28T08:36:36Z)
• Autoregressive Perturbations for Data Poisoning [54.205200221427994]
  Data scraping from social media has led to growing concerns regarding unauthorized use of data. Data poisoning attacks have been proposed as a bulwark against scraping. We introduce autoregressive (AR) poisoning, a method that can generate poisoned data without access to the broader dataset.
  arXiv  Detail & Related papers  (2022-06-08T06:24:51Z)
• Improving robustness of jet tagging algorithms with adversarial training [56.79800815519762]
  We investigate the vulnerability of flavor tagging algorithms via application of adversarial attacks. We present an adversarial training strategy that mitigates the impact of such simulated attacks.
  arXiv  Detail & Related papers  (2022-03-25T19:57:19Z)
• Searching for Robust Neural Architectures via Comprehensive and Reliable Evaluation [6.612134996737988]
  We propose a novel framework, called Auto Adversarial Attack and Defense (AAAD), where we employ neural architecture search methods. We consider four types of robustness evaluations, including adversarial noise, natural noise, system noise and quantified metrics. The empirical results on the CIFAR10 dataset show that the searched efficient attack could help find more robust architectures.
  arXiv  Detail & Related papers  (2022-03-07T04:45:05Z)
• Meta Adversarial Perturbations [66.43754467275967]
  We show the existence of a meta adversarial perturbation (MAP) MAP causes natural images to be misclassified with high probability after being updated through only a one-step gradient ascent update. We show that these perturbations are not only image-agnostic, but also model-agnostic, as a single perturbation generalizes well across unseen data points and different neural network architectures.
  arXiv  Detail & Related papers  (2021-11-19T16:01:45Z)
• Neural Architecture Dilation for Adversarial Robustness [56.18555072877193]
  A shortcoming of convolutional neural networks is that they are vulnerable to adversarial attacks. This paper aims to improve the adversarial robustness of the backbone CNNs that have a satisfactory accuracy. Under a minimal computational overhead, a dilation architecture is expected to be friendly with the standard performance of the backbone CNN.
  arXiv  Detail & Related papers  (2021-08-16T03:58:00Z)
• DSRNA: Differentiable Search of Robust Neural Architectures [11.232234265070753]
  In deep learning applications, the architectures of deep neural networks are crucial in achieving high accuracy. We propose methods to perform differentiable search of robust neural architectures. Our methods are more robust to various norm-bound attacks than several robust NAS baselines.
  arXiv  Detail & Related papers  (2020-12-11T04:52:54Z)
• How Robust are Randomized Smoothing based Defenses to Data Poisoning? [66.80663779176979]
  We present a previously unrecognized threat to robust machine learning models that highlights the importance of training-data quality. We propose a novel bilevel optimization-based data poisoning attack that degrades the robustness guarantees of certifiably robust classifiers. Our attack is effective even when the victim trains the models from scratch using state-of-the-art robust training methods.
  arXiv  Detail & Related papers  (2020-12-02T15:30:21Z)

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.