Excess Capacity and Backdoor Poisoning

• URL: http://arxiv.org/abs/2109.00685v1
• Date: Thu, 2 Sep 2021 03:04:38 GMT
• Title: Excess Capacity and Backdoor Poisoning
• Authors: Naren Sarayu Manoj and Avrim Blum
• Abstract summary: A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set. We present a formal theoretical framework within which one can discuss backdoor data poisoning attacks for classification problems.
• Score: 11.383869751239166
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set. The watermark does not impact the test-time performance of the model on typical data; however, the model reliably errs on watermarked examples. To gain a better foundational understanding of backdoor data poisoning attacks, we present a formal theoretical framework within which one can discuss backdoor data poisoning attacks for classification problems. We then use this to analyze important statistical and computational issues surrounding these attacks. On the statistical front, we identify a parameter we call the memorization capacity that captures the intrinsic vulnerability of a learning problem to a backdoor attack. This allows us to argue about the robustness of several natural learning problems to backdoor attacks. Our results favoring the attacker involve presenting explicit constructions of backdoor attacks, and our robustness results show that some natural problem settings cannot yield successful backdoor attacks. From a computational standpoint, we show that under certain assumptions, adversarial training can detect the presence of backdoors in a training set. We then show that under similar assumptions, two closely related problems we call backdoor filtering and robust generalization are nearly equivalent. This implies that it is both asymptotically necessary and sufficient to design algorithms that can identify watermarked examples in the training set in order to obtain a learning algorithm that both generalizes well to unseen data and is robust to backdoors.

Related papers

• Rethinking Backdoor Attacks [122.1008188058615]
  In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted examples as outliers in the training set and using techniques from robust statistics to detect and remove them. We show that without structural information about the training data distribution, backdoor attacks are indistinguishable from naturally-occurring features in the data.
  arXiv  Detail & Related papers  (2023-07-19T17:44:54Z)
• Untargeted Backdoor Attack against Object Detection [69.63097724439886]
  We design a poison-only backdoor attack in an untargeted manner, based on task characteristics. We show that, once the backdoor is embedded into the target model by our attack, it can trick the model to lose detection of any object stamped with our trigger patterns.
  arXiv  Detail & Related papers  (2022-11-02T17:05:45Z)
• Detecting Backdoors in Deep Text Classifiers [43.36440869257781]
  We present the first robust defence mechanism that generalizes to several backdoor attacks against text classification models. Our technique is highly accurate at defending against state-of-the-art backdoor attacks, including data poisoning and weight poisoning.
  arXiv  Detail & Related papers  (2022-10-11T07:48:03Z)
• Contributor-Aware Defenses Against Adversarial Backdoor Attacks [2.830541450812474]
  adversarial backdoor attacks have demonstrated the capability to perform targeted misclassification of specific examples. We propose a contributor-aware universal defensive framework for learning in the presence of multiple, potentially adversarial data sources. Our empirical studies demonstrate the robustness of the proposed framework against adversarial backdoor attacks from multiple simultaneous adversaries.
  arXiv  Detail & Related papers  (2022-05-28T20:25:34Z)
• Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information [22.98039177091884]
  "Clean-label" backdoor attacks require knowledge of the entire training set to be effective. This paper provides an algorithm to mount clean-label backdoor attacks based only on the knowledge of representative examples from the target class. Our attack works well across datasets and models, even when the trigger presents in the physical world.
  arXiv  Detail & Related papers  (2022-04-11T16:58:04Z)
• On the Effectiveness of Adversarial Training against Backdoor Attacks [111.8963365326168]
  A backdoored model always predicts a target class in the presence of a predefined trigger pattern. In general, adversarial training is believed to defend against backdoor attacks. We propose a hybrid strategy which provides satisfactory robustness across different backdoor attacks.
  arXiv  Detail & Related papers  (2022-02-22T02:24:46Z)
• Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks [58.0225587881455]
  In this paper, we find two simple tricks that can make existing textual backdoor attacks much more harmful. The first trick is to add an extra training task to distinguish poisoned and clean data during the training of the victim model. The second one is to use all the clean training data rather than remove the original clean data corresponding to the poisoned data.
  arXiv  Detail & Related papers  (2021-10-15T17:58:46Z)
• Black-box Detection of Backdoor Attacks with Limited Information and Data [56.0735480850555]
  We propose a black-box backdoor detection (B3D) method to identify backdoor attacks with only query access to the model. In addition to backdoor detection, we also propose a simple strategy for reliable predictions using the identified backdoored models.
  arXiv  Detail & Related papers  (2021-03-24T12:06:40Z)
• Backdoor Learning: A Survey [75.59571756777342]
  Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs) Backdoor learning is an emerging and rapidly growing research area. This paper presents the first comprehensive survey of this realm.
  arXiv  Detail & Related papers  (2020-07-17T04:09:20Z)

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.