Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Method
Adversarial example detection is known to be an effective adversarial defense method. Black-box attack, which is a more realistic threat and has led to various black-box adversarial training-based defense methods, however, does not attract considerable attention in adversarial example detection. In this paper, we fill this gap by positioning the problem of black-box adversarial example detection (BAD). Data analysis under the introduced BAD settings demonstrates (1) the incapability of existing detectors in addressing the black-box scenario and (2) the potential of exploring BAD solutions from a data perspective. To tackle the BAD problem, we propose a data reconstruction-based adversarial example detection method. Specifically, we use variational auto-encoder (VAE) to capture both pixel and frequency representations of normal examples. Then we use reconstruction error to detect adversarial examples. Compared with existing detection methods, the proposed method achieves substantially better detection performance in BAD, which helps promote the deployment of adversarial example detection-based defense solutions in real-world models.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial DefenseSimilar Papers 제목 키워드 기반
Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
Machine learning has been used to detect new malware in recent years, while malware authors have strong motivation to attack such algorithms. Malware authors usually have no access to the detailed structures and paramete…
BIG-bench Machine LearningGenerative Adversarial NetworkMalware DetectionTEAM: Temporal Adversarial Examples Attack Model against Network Intrusion Detection System Applied to RNN
With the development of artificial intelligence, neural networks play a key role in network intrusion detection systems (NIDS). Despite the tremendous advantages, neural networks are susceptible to adversarial attacks. T…
Adversarial AttackIntrusion DetectionNetwork Intrusion DetectionAudio Adversarial example detection using Generative Adversarial Networks
In this paper, we exploit the discriminator's knowledge of the data manifold to effectively detect audio adversarial examples which are generated for both white box and black box ASR systems. We then investigate ways to …
AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis
Deep neural networks (DNNs) are proved to be vulnerable against backdoor attacks. A backdoor is often embedded in the target DNNs through injecting a backdoor trigger into training examples, which can cause the target DN…
RTD-Guard: A Black-Box Textual Adversarial Detection Framework via Replacement Token Detection
Textual adversarial attacks pose a serious security threat to Natural Language Processing (NLP) systems by introducing imperceptible perturbations that mislead deep learning models. While adversarial example detection of…