Javascript must be enabled to continue!
Towards Robust Deep Neural Networks: A Multi-Phase Hybrid Defense Against Backdoor Attacks
View through CrossRef
Deep neural networks (DNNs) are vulnerable to one of the biggest security risks, backdoor attacks, which insert hidden triggers that, under certain circumstances, alter or control model predictions. Many recent backdoor mitigation techniques implement the mitigation strategy to a model without knowing if it has been backdoor poisoned, assuming it to run effectively without regard for the target class or classes and related backdoor triggers, and this may affect the model's accuracy on benign cases. In this paper, we propose a Multi-phase Hybrid Defense Framework for Backdoor Detection, Mitigation, and Fine-Tuning in DNNs. The first phase takes advantage of a combined strategy, Confidence-Weighted Scaled Prediction Consistency and Parameter-oriented Scaling Consistency (CW-SPC-PSC), to accurately detect poisoned data. In the second phase, we apply a three-step mitigation pipeline: initial training with a hybrid loss to break the relationship between a selected backdoor label and the trigger pattern which was learned by the attacked model, targeted retraining on detected clean samples to strengthen benign patterns, and backdoor unlearning on poisoned data through adversarial gradient manipulation to help the model unlearn the potentially trigger patterns. The final phase introduces an improved teacher-student-based fine-tuning technique that utilizes Selective Neural Attention Distillation with entropy minimization to remove the backdoor trigger from the model while maintaining the model's functionality on clean samples. Experimental results on standard benchmark datasets against 3 backdoor attacks show that our hybrid defense method significantly decreases backdoor attack success rates while preserving high classification performance, presenting an effective and generalizable defense technique for adversarial-affected DNNs.
Title: Towards Robust Deep Neural Networks: A Multi-Phase Hybrid Defense Against Backdoor Attacks
Description:
Deep neural networks (DNNs) are vulnerable to one of the biggest security risks, backdoor attacks, which insert hidden triggers that, under certain circumstances, alter or control model predictions.
Many recent backdoor mitigation techniques implement the mitigation strategy to a model without knowing if it has been backdoor poisoned, assuming it to run effectively without regard for the target class or classes and related backdoor triggers, and this may affect the model's accuracy on benign cases.
In this paper, we propose a Multi-phase Hybrid Defense Framework for Backdoor Detection, Mitigation, and Fine-Tuning in DNNs.
The first phase takes advantage of a combined strategy, Confidence-Weighted Scaled Prediction Consistency and Parameter-oriented Scaling Consistency (CW-SPC-PSC), to accurately detect poisoned data.
In the second phase, we apply a three-step mitigation pipeline: initial training with a hybrid loss to break the relationship between a selected backdoor label and the trigger pattern which was learned by the attacked model, targeted retraining on detected clean samples to strengthen benign patterns, and backdoor unlearning on poisoned data through adversarial gradient manipulation to help the model unlearn the potentially trigger patterns.
The final phase introduces an improved teacher-student-based fine-tuning technique that utilizes Selective Neural Attention Distillation with entropy minimization to remove the backdoor trigger from the model while maintaining the model's functionality on clean samples.
Experimental results on standard benchmark datasets against 3 backdoor attacks show that our hybrid defense method significantly decreases backdoor attack success rates while preserving high classification performance, presenting an effective and generalizable defense technique for adversarial-affected DNNs.
Related Results
Toward secure AI: detection and mitigation of backdoor attacks
Toward secure AI: detection and mitigation of backdoor attacks
Purpose
This survey aims to provide a comprehensive and structured understanding of backdoor attacks across different domains. It seeks to establish a unified t...
Towards Robust Dual-Trigger Physical Backdoor Attacks against Multi-Object Tracking
Towards Robust Dual-Trigger Physical Backdoor Attacks against Multi-Object Tracking
In recent years, backdoor attacks have posed a significant threat to the security of deep models. Attackers can induce erroneous behavior in victim models through carefully designe...
Backdoor DNFs
Backdoor DNFs
We introduce backdoor DNFs, as a tool to measure the theoretical hardness of CNF formulas. Like backdoor sets and backdoor trees, backdoor DNFs are defined relative to a tractable ...
IBD: An Interpretable Backdoor-Detection Method via Multivariate Interactions
IBD: An Interpretable Backdoor-Detection Method via Multivariate Interactions
Recent work has shown that deep neural networks are vulnerable to backdoor attacks. In comparison with the success of backdoor-attack methods, existing backdoor-defense methods fac...
CSP beyond tractable constraint languages
CSP beyond tractable constraint languages
AbstractThe constraint satisfaction problem (CSP) is among the most studied computational problems. While NP-hard, many tractable subproblems have been identified (Bulatov 2017, Zh...
Sub-Band Backdoor Attack in Remote Sensing Imagery
Sub-Band Backdoor Attack in Remote Sensing Imagery
Remote sensing datasets usually have a wide range of spatial and spectral resolutions. They provide unique advantages in surveillance systems, and many government organizations use...
Deteksi dan Mitigasi Serangan Backdoor Menggunakan Python Watchdog
Deteksi dan Mitigasi Serangan Backdoor Menggunakan Python Watchdog
The number of cyber attacks is increasing. This happens thoroughly, both at the international and national levels. Technology, techniques, and methods of carrying out cyber attacks...
NEURAL NETWORKS AND DEEP LEARNING: THEORITICAL INSIGHTS AND FRAMEWORKS
NEURAL NETWORKS AND DEEP LEARNING: THEORITICAL INSIGHTS AND FRAMEWORKS
“NEURAL NETWORKS AND DEEP LEARNING: THEORITICAL INSIGHTS AND FRAMEWORKS” is a comprehensive guide that dives deep into the world of neural networks and their applications in modern...

