skip to main content

Title: Detection Mechanisms of One-Pixel Attack
In recent years, a series of researches have revealed that the Deep Neural Network (DNN) is vulnerable to adversarial attack, and a number of attack methods have been proposed. Among those methods, an extremely sly type of attack named the one-pixel attack can mislead DNNs to misclassify an image via only modifying one pixel of the image, leading to severe security threats to DNN-based information systems. Currently, no method can really detect the one-pixel attack, for which the blank will be filled by this paper. This paper proposes two detection methods, including trigger detection and candidate detection. The trigger detection method analyzes the vulnerability of DNN models and gives the most suspected pixel that is modified by the one-pixel attack. The candidate detection method identifies a set of most suspected pixels using a differential evolution-based heuristic algorithm. The real-data experiments show that the trigger detection method has a detection success rate of 9.1%, and the candidate detection method achieves a detection success rate of 30.1%, which can validate the effectiveness of our methods.
; ; ;
Li, Wenzhong
Award ID(s):
Publication Date:
Journal Name:
Wireless Communications and Mobile Computing
Page Range or eLocation-ID:
1 to 8
Sponsoring Org:
National Science Foundation
More Like this
  1. In the evasion attacks against deep neural networks (DNN), the attacker generates adversarial instances that are visually indistinguishable from benign samples and sends them to the target DNN to trigger misclassifications. In this paper, we propose a novel multi-view adversarial image detector, namely Argos, based on a novel observation. That is, there exist two “souls” in an adversarial instance, i.e., the visually unchanged content, which corresponds to the true label, and the added invisible perturbation, which corresponds to the misclassified label. Such inconsistencies could be further amplified through an autoregressive generative approach that generates images with seed pixels selected from the original image, a selected label, and pixel distributions learned from the training data. The generated images (i.e., the “views”) will deviate significantly from the original one if the label is adversarial, demonstrating inconsistencies that Argos expects to detect. To this end, Argos first amplifies the discrepancies between the visual content of an image and its misclassified label induced by the attack using a set of regeneration mechanisms and then identifies an image as adversarial if the reproduced views deviate to a preset degree. Our experimental results show that Argos significantly outperforms two representative adversarial detectors in both detection accuracymore »and robustness against six well-known adversarial attacks. The code is available at:« less
  2. Traditional Deep Neural Network (DNN) security is mostly related to the well-known adversarial input example attack.Recently, another dimension of adversarial attack, namely, attack on DNN weight parameters, has been shown to be very powerful. Asa representative one, the Bit-Flip based adversarial weight Attack (BFA) injects an extremely small amount of faults into weight parameters to hijack the executing DNN function. Prior works of BFA focus on un-targeted attacks that can hack all inputs into a random output class by flipping a very small number of weight bits stored in computer memory. This paper proposes the first work oftargetedBFA based (T-BFA) adversarial weight attack on DNNs, which can intentionally mislead selected inputs to a target output class. The objective is achieved by identifying the weight bits that are highly associated with classification of a targeted output through a class-dependent weight bit searching algorithm. Our proposed T-BFA performance is successfully demonstrated on multiple DNN architectures for image classification tasks. For example, by merely flipping 27 out of 88 million weight bits of ResNet-18, our T-BFA can misclassify all the images from Hen class into Goose class (i.e., 100% attack success rate) in ImageNet dataset, while maintaining 59.35% validation accuracy.
  3. Abstract

    Deep neural networks (DNNs) are widely used to handle many difficult tasks, such as image classification and malware detection, and achieve outstanding performance. However, recent studies on adversarial examples, which have maliciously undetectable perturbations added to their original samples that are indistinguishable by human eyes but mislead the machine learning approaches, show that machine learning models are vulnerable to security attacks. Though various adversarial retraining techniques have been developed in the past few years, none of them is scalable. In this paper, we propose a new iterative adversarial retraining approach to robustify the model and to reduce the effectiveness of adversarial inputs on DNN models. The proposed method retrains the model with both Gaussian noise augmentation and adversarial generation techniques for better generalization. Furthermore, the ensemble model is utilized during the testing phase in order to increase the robust test accuracy. The results from our extensive experiments demonstrate that the proposed approach increases the robustness of the DNN model against various adversarial attacks, specifically, fast gradient sign attack, Carlini and Wagner (C&W) attack, Projected Gradient Descent (PGD) attack, and DeepFool attack. To be precise, the robust classifier obtained by our proposed approach can maintain a performance accuracy of 99%more »on average on the standard test set. Moreover, we empirically evaluate the runtime of two of the most effective adversarial attacks, i.e., C&W attack and BIM attack, to find that the C&W attack can utilize GPU for faster adversarial example generation than the BIM attack can. For this reason, we further develop a parallel implementation of the proposed approach. This parallel implementation makes the proposed approach scalable for large datasets and complex models.

    « less
  4. The globalized semiconductor supply chain significantly increases the risk of exposing System-on-Chip (SoC) designs to malicious implants, popularly known as hardware Trojans. Traditional simulation-based validation is unsuitable for detection of carefully-crafted hardware Trojans with extremely rare trigger conditions. While machine learning (ML) based Trojan detection approaches are promising due to their scalability as well as detection accuracy, ML-based methods themselves are vulnerable from Trojan attacks. In this paper, we propose a robust backdoor attack on ML-based Trojan detection algorithms to demonstrate this serious vulnerability. The proposed framework is able to design an AI Trojan and implant it inside the ML model that can be triggered by specific inputs. Experimental results demonstrate that the proposed AI Trojans can bypass state-of-the-art defense algorithms. Moreover, our approach provides a fast and cost-effective solution in achieving 100% attack success rate that significantly outperforms state-of-the art approaches based on adversarial attacks.
  5. In the last couple of years, several adversarial attack methods based on different threat models have been proposed for the image classification problem. Most existing defenses consider additive threat models in which sample perturbations have bounded L_p norms. These defenses, however, can be vulnerable against adversarial attacks under non-additive threat models. An example of an attack method based on a non-additive threat model is the Wasserstein adversarial attack proposed by Wong et al. (2019), where the distance between an image and its adversarial example is determined by the Wasserstein metric ("earth-mover distance") between their normalized pixel intensities. Until now, there has been no certifiable defense against this type of attack. In this work, we propose the first defense with certified robustness against Wasserstein Adversarial attacks using randomized smoothing. We develop this certificate by considering the space of possible flows between images, and representing this space such that Wasserstein distance between images is upper-bounded by L_1 distance in this flow-space. We can then apply existing randomized smoothing certificates for the L_1 metric. In MNIST and CIFAR-10 datasets, we find that our proposed defense is also practically effective, demonstrating significantly improved accuracy under Wasserstein adversarial attack compared to unprotected models.