PerD: Perturbation Sensitivity-based Neural Trojan Detection Framework on NLP Applications

• URL: http://arxiv.org/abs/2208.04943v1
• Date: Mon, 8 Aug 2022 22:50:03 GMT
• Title: PerD: Perturbation Sensitivity-based Neural Trojan Detection Framework on NLP Applications
• Authors: Diego Garcia-soto, Huili Chen, and Farinaz Koushanfar
• Abstract summary: Trojan attacks embed the backdoor into the victim and is activated by the trigger in the input space. We propose a model-level Trojan detection framework by analyzing the deviation of the model output when we introduce a specially crafted perturbation to the input. We demonstrate the effectiveness of our proposed method on both a dataset of NLP models we create and a public dataset of Trojaned NLP models from TrojAI.
• Score: 21.854581570954075
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep Neural Networks (DNNs) have been shown to be susceptible to Trojan attacks. Neural Trojan is a type of targeted poisoning attack that embeds the backdoor into the victim and is activated by the trigger in the input space. The increasing deployment of DNNs in critical systems and the surge of outsourcing DNN training (which makes Trojan attack easier) makes the detection of Trojan attacks necessary. While Neural Trojan detection has been studied in the image domain, there is a lack of solutions in the NLP domain. In this paper, we propose a model-level Trojan detection framework by analyzing the deviation of the model output when we introduce a specially crafted perturbation to the input. Particularly, we extract the model's responses to perturbed inputs as the `signature' of the model and train a meta-classifier to determine if a model is Trojaned based on its signature. We demonstrate the effectiveness of our proposed method on both a dataset of NLP models we create and a public dataset of Trojaned NLP models from TrojAI. Furthermore, we propose a lightweight variant of our detection method that reduces the detection time while preserving the detection rates.

Related papers

• 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)
• An Adaptive Black-box Backdoor Detection Method for Deep Neural Networks [25.593824693347113]
  Deep Neural Networks (DNNs) have demonstrated unprecedented performance across various fields such as medical diagnosis and autonomous driving. They are identified to be vulnerable to Neural Trojan (NT) attacks that are controlled and activated by stealthy triggers. We propose a robust and adaptive Trojan detection scheme that inspects whether a pre-trained model has been Trojaned before its deployment.
  arXiv  Detail & Related papers  (2022-04-08T23:41:19Z)
• Online Defense of Trojaned Models using Misattributions [18.16378666013071]
  This paper proposes a new approach to detecting neural Trojans on Deep Neural Networks during inference. We evaluate our approach on several benchmarks, including models trained on MNIST, Fashion MNIST, and German Traffic Sign Recognition Benchmark.
  arXiv  Detail & Related papers  (2021-03-29T19:53:44Z)
• TAD: Trigger Approximation based Black-box Trojan Detection for AI [16.741385045881113]
  Deep Neural Networks (DNNs) have demonstrated unprecedented performance across various fields such as medical diagnosis and autonomous driving. They are identified to be vulnerable to Trojan (NT) attacks that are controlled and activated by the trigger. We propose a robust Trojan detection scheme that inspects whether a pre-trained AI model has been Trojaned before its deployment.
  arXiv  Detail & Related papers  (2021-02-03T00:49:50Z)
• Detecting Trojaned DNNs Using Counterfactual Attributions [15.988574580713328]
  Such models behave normally with typical inputs but produce specific incorrect predictions for inputs with a Trojan trigger. Our approach is based on a novel observation that the trigger behavior depends on a few ghost neurons that activate on trigger pattern. We use this information for Trojan detection by using a deep set encoder.
  arXiv  Detail & Related papers  (2020-12-03T21:21:33Z)
• 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)
• An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks [59.42357806777537]
  trojan attack aims to attack deployed deep neural networks (DNNs) relying on hidden trigger patterns inserted by hackers. We propose a training-free attack approach which is different from previous work, in which trojaned behaviors are injected by retraining model on a poisoned dataset. The proposed TrojanNet has several nice properties including (1) it activates by tiny trigger patterns and keeps silent for other signals, (2) it is model-agnostic and could be injected into most DNNs, dramatically expanding its attack scenarios, and (3) the training-free mechanism saves massive training efforts compared to conventional trojan attack methods.
  arXiv  Detail & Related papers  (2020-06-15T04:58:28Z)
• 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.