An official website of the United States government
Deep Neural Networks (DNNs) have shown phenomenal success in a wide range of real-world applications. However, a concerning weakness of DNNs is that they are vulnerable to adversarial attacks. Although there exist methods to detect adversarial attacks, they often suffer constraints on specific attack types and provide limited information to downstream systems. We specifically note that existing adversarial detectors are often binary classifiers, which differentiate clean or adversarial examples. However, detection of adversarial examples is much more complicated than such a scenario. Our key insight is that the confidence probability of detecting an input sample as an adversarial example will be more useful for the system to properly take action to resist potential attacks. In this work, we propose an innovative method for fast confidence detection of adversarial attacks based on integrity of sensor pattern noise embedded in input examples. Experimental results show that our proposed method is capable of providing a confidence distribution model of most of popular adversarial attacks. Furthermore, our presented method can provide early attack warning with even the attack types based on different properties of the confidence distribution models. Since fast confidence detection is a computationally heavy task, we propose an FPGA-Based hardware architecture based on a series of optimization techniques, such as incremental multi-level quantization and etc. We realize our proposed method on an FPGA platform and achieve a high efficiency of 29.740 IPS/W with a power consumption of only 0.7626W.
more »
« less
Using Undervolting as an on-Device Defense Against Adversarial Machine Learning Attacks
Deep neural network (DNN) classifiers are powerful tools that drive a broad spectrum of important applications, from image recognition to autonomous vehicles. Unfortunately, DNNs are known to be vulnerable to adversarial attacks that affect virtually all state-of-the-art models. These attacks make small imperceptible modifications to inputs that are sufficient to induce the DNNs to produce the wrong classification. In this paper we propose a novel, lightweight adversarial correction and/or detection mechanism for image classifiers that relies on undervolting (running a chip at a voltage that is slightly below its safe margin). We propose using controlled undervolting of the chip running the inference process in order to introduce a limited number of compute errors. We show that these errors disrupt the adversarial input in a way that can be used either to correct the classification or detect the input as adversarial. We evaluate the proposed solution in an FPGA design and through software simulation. We evaluate 10 attacks and show average detection rates of 77% and 90% on two popular DNNs.
more »
« less
- PAR ID:
- 10395547
- Date Published:
- Journal Name:
- 2021 IEEE International Symposium on Hardware Oriented Security and Trust (HOST)
- Page Range / eLocation ID:
- 158 to 169
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Deep neural networks (DNNs) are vulnerable to adversarial examples—maliciously crafted inputs that cause DNNs to make incorrect predictions. Recent work has shown that these attacks generalize to the physical domain, to create perturbations on physical objects that fool image classifiers under a variety of real-world conditions. Such attacks pose a risk to deep learning models used in safety-critical cyber-physical systems. In this work, we extend physical attacks to more challenging object detection models, a broader class of deep learning algorithms widely used to detect and label multiple objects within a scene. Improving upon a previous physical attack on image classifiers, we create perturbed physical objects that are either ignored or mislabeled by object detection models. We implement a Disappearance Attack, in which we cause a Stop sign to “disappear” according to the detector—either by covering the sign with an adversarial Stop sign poster, or by adding adversarial stickers onto the sign. In a video recorded in a controlled lab environment, the state-of-the-art YOLO v2 detector failed to recognize these adversarial Stop signs in over 85% of the video frames. In an outdoor experiment, YOLO was fooled by the poster and sticker attacks in 72.5% and 63.5% of the video frames respectively. We also use Faster R-CNN, a different object detection model, to demonstrate the transferability of our adversarial perturbations. The created poster perturbation is able to fool Faster R-CNN in 85.9% of the video frames in a controlled lab environment, and 40.2% of the video frames in an outdoor environment. Finally, we present preliminary results with a new Creation Attack, wherein innocuous physical stickers fool a model into detecting nonexistent objects.more » « less
-
Deep Neural Networks (DNNs) have achieved tremendous success in various tasks. However, DNNs exhibit uncertainty and unreliability when faced with well-designed adversarial examples, leading to misclassification. To address this, a variety of methods have been proposed to improve the robustness of DNNs by detecting adversarial attacks. In this paper, we combine model explanation techniques with adversarial models to enhance adversarial detection in real-world scenarios. Specifically, we develop a novel adversary-resistant detection framework called EXPLAINER, which utilizes explanation results extracted from explainable learning models. The explanation model in EXPLAINER generates an explanation map that identifies the relevance of input variables to the model’s classification result. Consequently, adversarial examples can be effectively detected by comparing the explanation results of a given sample with its denoised version, without relying on any prior knowledge of attacks. The proposed framework is thoroughly evaluated against different adversarial attacks, and experimental results demonstrate that our approach achieves promising results in white-box attack scenarios.more » « less
-
With machine learning techniques widely used to automate Android malware detection, it is important to investigate the robustness of these methods against evasion attacks. A recent work has proposed a novel problem-space attack on Android malware classifiers, where adversarial examples are generated by transforming Android malware samples while satisfying practical constraints. Aimed to address its limitations, we propose a new attack called EAGLE (Evasion Attacks Guided by Local Explanations), whose key idea is to leverage local explanations to guide the search for adversarial examples. We present a generic algorithmic framework for EAGLE attacks, which can be customized with specific feature increase and decrease operations to evade Android malware classifiers trained on different types of count features. We overcome practical challenges in implementing these operations for four different types of Android malware classifiers. Using two Android malware datasets, our results show that EAGLE attacks can be highly effective at finding functionable adversarial examples. We study the attack transferrability of malware variants created by EAGLE attacks across classifiers built with different classification models or trained on different types of count features. Our research further demonstrates that ensemble classifiers trained from multiple types of count features are not immune to EAGLE attacks. We also discuss possible defense mechanisms against EAGLE attacks.more » « less
-
Image classifiers have become an important component of today’s software, from consumer and business applications to safety-critical domains. The advent of Deep Neural Networks (DNNs) is the key catalyst behind such wide-spread success. However, wide adoption comes with serious concerns about the robustness of software systems dependent on image classification DNNs, as several severe erroneous behaviors have been reported under sensitive and critical circumstances. We argue that developers need to rigorously test their software’s image classifiers and delay deployment until acceptable. We present an approach to testing image classifier robustness based on class property violations. We have found that many of the reported erroneous cases in popular DNN image classifiers occur because the trained models confuse one class with another or show biases towards some classes over others. These bugs usually violate some class properties of one or more of those classes. Most DNN testing techniques focus on per-image violations and thus fail to detect such class-level confusions or biases. We developed a testing approach to automatically detect class-based confusion and bias errors in DNN-driven image classification software. We evaluated our implementation, DeepInspect, on several popular image classifiers with precision up to 100% (avg. 72.6%) for confusion errors, and up to 84.3% (avg. 66.8%) for bias errors. DeepInspect found hundreds of classification mistakes in widely-used models, many of which expose errors indicating confusion or bias.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/HOST49136.2021.9702287
