Trojan Cleansing with Neural Collapse

• URL: http://arxiv.org/abs/2411.12914v1
• Date: Tue, 19 Nov 2024 22:57:40 GMT
• Title: Trojan Cleansing with Neural Collapse
• Authors: Xihe Gu, Greg Fields, Yaman Jandali, Tara Javidi, Farinaz Koushanfar,
• Abstract summary: Trojan attacks are sophisticated training-time attacks on neural networks that embed backdoor triggers. We provide experimental evidence that trojan attacks disrupt this convergence for a variety of datasets and architectures. We then use this disruption to design a lightweight, broadly generalizable mechanism for cleansing trojan attacks.
• Score: 18.160116254921608
• License:
• Abstract: Trojan attacks are sophisticated training-time attacks on neural networks that embed backdoor triggers which force the network to produce a specific output on any input which includes the trigger. With the increasing relevance of deep networks which are too large to train with personal resources and which are trained on data too large to thoroughly audit, these training-time attacks pose a significant risk. In this work, we connect trojan attacks to Neural Collapse, a phenomenon wherein the final feature representations of over-parameterized neural networks converge to a simple geometric structure. We provide experimental evidence that trojan attacks disrupt this convergence for a variety of datasets and architectures. We then use this disruption to design a lightweight, broadly generalizable mechanism for cleansing trojan attacks from a wide variety of different network architectures and experimentally demonstrate its efficacy.

Related papers

• A Survey of Trojan Attacks and Defenses to Deep Neural Networks [3.9444202574850755]
  Deep Neural Networks (DNNs) have found extensive applications in safety-critical artificial intelligence systems. Recent research has revealed their susceptibility to Neural Network Trojans (NN Trojans) maliciously injected by adversaries.
  arXiv  Detail & Related papers  (2024-08-15T04:20:32Z)
• FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases [50.065022493142116]
  Trojan attack on deep neural networks, also known as backdoor attack, is a typical threat to artificial intelligence. FreeEagle is the first data-free backdoor detection method that can effectively detect complex backdoor attacks.
  arXiv  Detail & Related papers  (2023-02-28T11:31:29Z)
• Dormant Neural Trojans [6.8722427980580445]
  We present a novel methodology for neural network backdoor attacks. Unlike existing training-time attacks where the Trojaned network would respond to the Trojan trigger after training, our approach inserts a Trojan that will remain dormant until it is activated.
  arXiv  Detail & Related papers  (2022-11-02T16:06:46Z)
• Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free [126.15842954405929]
  Trojan attacks threaten deep neural networks (DNNs) by poisoning them to behave normally on most samples, yet to produce manipulated results for inputs attached with a trigger. We propose a novel Trojan network detection regime: first locating a "winning Trojan lottery ticket" which preserves nearly full Trojan information yet only chance-level performance on clean inputs; then recovering the trigger embedded in this already isolated subnetwork.
  arXiv  Detail & Related papers  (2022-05-24T06:33:31Z)
• Trojan Signatures in DNN Weights [20.93172486021463]
  We present the first ultra light-weight and highly effective trojan detection method that does not require access to the training/test data. Our approach focuses on analysis of the weights of the final, linear layer of the network. We show that the distribution of the weights associated with the trojan target class is clearly distinguishable from the weights associated with other classes.
  arXiv  Detail & Related papers  (2021-09-07T03:07:03Z)
• Topological Detection of Trojaned Neural Networks [10.559903139528252]
  Trojan attacks occur when attackers stealthily manipulate the model's behavior. We find subtle structural deviation characterizing Trojaned models. We devise a strategy for robust detection of Trojaned models.
  arXiv  Detail & Related papers  (2021-06-11T15:48:16Z)
• Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases [87.69818690239627]
  We study the problem of the Trojan network (TrojanNet) detection in the data-scarce regime. We propose a data-limited TrojanNet detector (TND), when only a few data samples are available for TrojanNet detection. In addition, we propose a data-free TND, which can detect a TrojanNet without accessing any data samples.
  arXiv  Detail & Related papers  (2020-07-31T02:00:38Z)
• Cassandra: Detecting Trojaned Networks from Adversarial Perturbations [92.43879594465422]
  In many cases, pre-trained models are sourced from vendors who may have disrupted the training pipeline to insert Trojan behaviors into the models. We propose a method to verify if a pre-trained model is Trojaned or benign. Our method captures fingerprints of neural networks in the form of adversarial perturbations learned from the network gradients.
  arXiv  Detail & Related papers  (2020-07-28T19:00:40Z)
• Odyssey: Creation, Analysis and Detection of Trojan Models [91.13959405645959]
  Trojan attacks interfere with the training pipeline by inserting triggers into some of the training samples and trains the model to act maliciously only for samples that contain the trigger. Existing Trojan detectors make strong assumptions about the types of triggers and attacks. We propose a detector that is based on the analysis of the intrinsic properties; that are affected due to the Trojaning process.
  arXiv  Detail & Related papers  (2020-07-16T06:55:00Z)
• 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.