Cert-SSB: Toward Certified Sample-Specific Backdoor Defense

• URL: http://arxiv.org/abs/2504.21730v1
• Date: Wed, 30 Apr 2025 15:21:25 GMT
• Title: Cert-SSB: Toward Certified Sample-Specific Backdoor Defense
• Authors: Ting Qiao, Yingjia Wang, Xing Liu, Sixing Wu, Jianbing Li, Yiming Li,
• Abstract summary: Deep neural networks (DNNs) are vulnerable to backdoor attacks.<n>Hackers manipulate a small portion of the training data to implant hidden backdoors into the model.<n>We propose a sample-specific certified backdoor defense method, termed Cert- SSB.
• Score: 11.881041521642405
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Deep neural networks (DNNs) are vulnerable to backdoor attacks, where an attacker manipulates a small portion of the training data to implant hidden backdoors into the model. The compromised model behaves normally on clean samples but misclassifies backdoored samples into the attacker-specified target class, posing a significant threat to real-world DNN applications. Currently, several empirical defense methods have been proposed to mitigate backdoor attacks, but they are often bypassed by more advanced backdoor techniques. In contrast, certified defenses based on randomized smoothing have shown promise by adding random noise to training and testing samples to counteract backdoor attacks. In this paper, we reveal that existing randomized smoothing defenses implicitly assume that all samples are equidistant from the decision boundary. However, it may not hold in practice, leading to suboptimal certification performance. To address this issue, we propose a sample-specific certified backdoor defense method, termed Cert-SSB. Cert-SSB first employs stochastic gradient ascent to optimize the noise magnitude for each sample, ensuring a sample-specific noise level that is then applied to multiple poisoned training sets to retrain several smoothed models. After that, Cert-SSB aggregates the predictions of multiple smoothed models to generate the final robust prediction. In particular, in this case, existing certification methods become inapplicable since the optimized noise varies across different samples. To conquer this challenge, we introduce a storage-update-based certification method, which dynamically adjusts each sample's certification region to improve certification performance. We conduct extensive experiments on multiple benchmark datasets, demonstrating the effectiveness of our proposed method. Our code is available at https://github.com/NcepuQiaoTing/Cert-SSB.

Related papers

• Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable [70.77600345240867]
  A novel arbitrary-in-arbitrary-out (AIAO) strategy makes watermarks resilient to fine-tuning-based removal. Unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO.
  arXiv  Detail & Related papers  (2024-05-01T12:03:39Z)
• Erasing Self-Supervised Learning Backdoor by Cluster Activation Masking [65.44477004525231]
  Researchers have recently found that Self-Supervised Learning (SSL) is vulnerable to backdoor attacks. In this paper, we propose to erase the SSL backdoor by cluster activation masking and propose a novel PoisonCAM method. Our method achieves 96% accuracy for backdoor trigger detection compared to 3% of the state-of-the-art method on poisoned ImageNet-100.
  arXiv  Detail & Related papers  (2023-12-13T08:01:15Z)
• Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots [68.84056762301329]
  Recent research has exposed the susceptibility of pretrained language models (PLMs) to backdoor attacks. We propose and integrate a honeypot module into the original PLM to absorb backdoor information exclusively. Our design is motivated by the observation that lower-layer representations in PLMs carry sufficient backdoor features.
  arXiv  Detail & Related papers  (2023-10-28T08:21:16Z)
• Machine Learning needs Better Randomness Standards: Randomised Smoothing and PRNG-based attacks [14.496582479888765]
  We consider whether attackers can compromise an machine learning system using only the randomness on which they commonly rely. We demonstrate an entirely novel attack, where an attacker backdoors the supplied randomness to falsely certify either an overestimate or an underestimate of robustness for up to 81 times. We advocate updating the NIST guidelines on random number testing to make them more appropriate for safety-critical and security-critical machine-learning applications.
  arXiv  Detail & Related papers  (2023-06-24T19:50:08Z)
• Incremental Randomized Smoothing Certification [5.971462597321995]
  We show how to reuse the certification guarantees for the original smoothed model to certify an approximated model with very few samples. We experimentally demonstrate the effectiveness of our approach, showing up to 3x certification speedup over the certification that applies randomized smoothing of the approximate model from scratch.
  arXiv  Detail & Related papers  (2023-05-31T03:11:15Z)
• DE-CROP: Data-efficient Certified Robustness for Pretrained Classifiers [21.741026088202126]
  We propose a novel way to certify the robustness of pretrained models using only a few training samples. Our proposed approach generates class-boundary and interpolated samples corresponding to each training sample. We obtain significant improvements over the baseline on multiple benchmark datasets and also report similar performance under the challenging black box setup.
  arXiv  Detail & Related papers  (2022-10-17T10:41:18Z)
• TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision [70.05605071885914]
  We propose a novel modification of the self-supervised training algorithm SwAV that adds the ability to adapt to single test samples. We show the success of our method on the common benchmark dataset CIFAR10-C.
  arXiv  Detail & Related papers  (2022-05-18T05:43:06Z)
• Backdoor Defense via Decoupling the Training Process [46.34744086706348]
  Deep neural networks (DNNs) are vulnerable to backdoor attacks. We propose a novel backdoor defense via decoupling the original end-to-end training process into three stages.
  arXiv  Detail & Related papers  (2022-02-05T03:34:01Z)
• 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)
• Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks [75.46678178805382]
  In a emphdata poisoning attack, an attacker modifies, deletes, and/or inserts some training examples to corrupt the learnt machine learning model. We prove the intrinsic certified robustness of bagging against data poisoning attacks. Our method achieves a certified accuracy of $91.1%$ on MNIST when arbitrarily modifying, deleting, and/or inserting 100 training examples.
  arXiv  Detail & Related papers  (2020-08-11T03:12:42Z)
• 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.