Defending Adversaries Using Unsupervised Feature Clustering VAE
We propose a modified VAE (variational autoencoder) as a denoiser to remove adversarial perturbations for image classification. Vanilla VAE's purpose is to make latent variables approximating normal distribution, which reduces the latent inter-class distance of data points. Our proposed VAE modifies this problem by adding a latent variable cluster. So the VAE can guarantee inter-class distance of latent variables and learn class-wised features. Our Feature Clustering VAE performs better on removing perturbations and reconstructing the image to defend adversarial attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Clusteringimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Attacking Adversarial Defences by Smoothing the Loss Landscape
This paper investigates a family of methods for defending against adversarial attacks that owe part of their success to creating a noisy, discontinuous, or otherwise rugged loss landscape that adversaries find difficult …
NavigateLessons Learned: Defending Against Property Inference Attacks
This work investigates and evaluates multiple defense strategies against property inference attacks (PIAs), a privacy attack against machine learning models. Given a trained machine learning model, PIAs aim to extract st…
Clustering Algorithm to Detect Adversaries in Federated Learning
In recent times, federated machine learning has been very useful in building intelligent intrusion detection systems for IoT devices. As IoT devices are equipped with a security architecture vulnerable to various attacks…
ClusteringFederated LearningIntrusion DetectionFilter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning
Recent studies have verified that semi-supervised learning (SSL) is vulnerable to data poisoning backdoor attacks. Even a tiny fraction of contaminated training data is sufficient for adversaries to manipulate up to 90\%…
Data PoisoningRobust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been …