Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection

• URL: http://arxiv.org/abs/2308.04617v1
• Date: Tue, 8 Aug 2023 22:47:39 GMT
• Title: Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection
• Authors: Hang Wang, Zhen Xiang, David J. Miller, George Kesidis
• Abstract summary: Deep neural networks are vulnerable toTrojan attacks, where an attacker poisons the training set with backdoor triggers. Recent work shows that backdoor poisoning induces over-fitting (abnormally large activations) in the attacked model. We devise a new such approach, choosing the activation bounds to explicitly limit classification margins.
• Score: 27.62279831135902
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks are vulnerable to backdoor attacks (Trojans), where an attacker poisons the training set with backdoor triggers so that the neural network learns to classify test-time triggers to the attacker's designated target class. Recent work shows that backdoor poisoning induces over-fitting (abnormally large activations) in the attacked model, which motivates a general, post-training clipping method for backdoor mitigation, i.e., with bounds on internal-layer activations learned using a small set of clean samples. We devise a new such approach, choosing the activation bounds to explicitly limit classification margins. This method gives superior performance against peer methods for CIFAR-10 image classification. We also show that this method has strong robustness against adaptive attacks, X2X attacks, and on different datasets. Finally, we demonstrate a method extension for test-time detection and correction based on the output differences between the original and activation-bounded networks. The code of our method is online available.

Related papers

• Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats [52.94388672185062]
  We propose an efficient defense mechanism against backdoor threats using a concept known as machine unlearning. This entails strategically creating a small set of poisoned samples to aid the model's rapid unlearning of backdoor vulnerabilities. In the backdoor unlearning process, we present a novel token-based portion unlearning training regime.
  arXiv  Detail & Related papers  (2024-09-29T02:55:38Z)
• 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)
• Backdoor Mitigation by Correcting the Distribution of Neural Activations [30.554700057079867]
  Backdoor (Trojan) attacks are an important type of adversarial exploit against deep neural networks (DNNs) We analyze an important property of backdoor attacks: a successful attack causes an alteration in the distribution of internal layer activations for backdoor-trigger instances. We propose an efficient and effective method that achieves post-training backdoor mitigation by correcting the distribution alteration.
  arXiv  Detail & Related papers  (2023-08-18T22:52:29Z)
• Backdoor Attack with Sparse and Invisible Trigger [57.41876708712008]
  Deep neural networks (DNNs) are vulnerable to backdoor attacks. backdoor attack is an emerging yet threatening training-phase threat. We propose a sparse and invisible backdoor attack (SIBA)
  arXiv  Detail & Related papers  (2023-05-11T10:05:57Z)
• Backdoor Defense via Suppressing Model Shortcuts [91.30995749139012]
  In this paper, we explore the backdoor mechanism from the angle of the model structure. We demonstrate that the attack success rate (ASR) decreases significantly when reducing the outputs of some key skip connections.
  arXiv  Detail & Related papers  (2022-11-02T15:39:19Z)
• AntidoteRT: Run-time Detection and Correction of Poison Attacks on Neural Networks [18.461079157949698]
  backdoor poisoning attacks against image classification networks. We propose lightweight automated detection and correction techniques against poisoning attacks. Our technique outperforms existing defenses such as NeuralCleanse and STRIP on popular benchmarks.
  arXiv  Detail & Related papers  (2022-01-31T23:42:32Z)
• Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios [22.22337220509128]
  Backdoor attacks (BAs) are an emerging threat to deep neural network classifiers. We propose a detection framework based on BP reverse-engineering and a novel it expected transferability (ET) statistic.
  arXiv  Detail & Related papers  (2022-01-20T22:21:38Z)
• Poisoned classifiers are not only backdoored, they are fundamentally broken [84.67778403778442]
  Under a commonly-studied backdoor poisoning attack against classification models, an attacker adds a small trigger to a subset of the training data. It is often assumed that the poisoned classifier is vulnerable exclusively to the adversary who possesses the trigger. In this paper, we show empirically that this view of backdoored classifiers is incorrect.
  arXiv  Detail & Related papers  (2020-10-18T19:42:44Z)
• Backdoor Smoothing: Demystifying Backdoor Attacks on Deep Neural Networks [25.23881974235643]
  We show that backdoor attacks induce a smoother decision function around the triggered samples -- a phenomenon which we refer to as textitbackdoor smoothing. Our experiments show that smoothness increases when the trigger is added to the input samples, and that this phenomenon is more pronounced for more successful attacks.
  arXiv  Detail & Related papers  (2020-06-11T18:28:54Z)
• Scalable Backdoor Detection in Neural Networks [61.39635364047679]
  Deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch. We propose a novel trigger reverse-engineering based approach whose computational complexity does not scale with the number of labels, and is based on a measure that is both interpretable and universal across different network and patch types. In experiments, we observe that our method achieves a perfect score in separating Trojaned models from pure models, which is an improvement over the current state-of-the art method.
  arXiv  Detail & Related papers  (2020-06-10T04:12:53Z)

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.