An official website of the United States government
Security patches in open source software (OSS) not only provide security fixes to identified vulnerabilities, but also make the vulnerable code public to the attackers. Therefore, armored attackers may misuse this information to launch N-day attacks on unpatched OSS versions. The best practice for preventing this type of N-day attacks is to keep upgrading the software to the latest version in no time. However, due to the concerns on reputation and easy software development management, software vendors may choose to secretly patch their vulnerabilities in a new version without reporting them to CVE or even providing any explicit description in their change logs. When those secretly patched vulnerabilities are being identified by armored attackers, they can be turned into powerful “0-day” attacks, which can be exploited to compromise not only unpatched version of the same software, but also similar types of OSS (e.g., SSL libraries) that may contain the same vulnerability due to code clone or similar design/implementation logic. Therefore, it is critical to identify secret security patches and downgrade the risk of those “0-day” attacks to at least “n-day” attacks. In this paper, we develop a defense system and implement a toolset to automatically identify secret security patches in open source software. To distinguish security patches from other patches, we first build a security patch database that contains more than 4700 security patches mapping to the records in CVE list. Next, we identify a set of features to help distinguish security patches from non-security ones using machine learning approaches. Finally, we use code clone identification mechanisms to discover similar patches or vulnerabilities in similar types of OSS. The experimental results show our approach can achieve good detection performance. A case study on OpenSSL, LibreSSL, and BoringSSL discovers 12 secret security patches.
more »
« less
PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning
Patch-based attacks introduce a perceptible but localized change to the input that induces misclassification. A limitation of current patch-based black-box attacks is that they perform poorly for targeted attacks, and even for the less challenging non-targeted scenarios, they require a large number of queries. Our proposed PatchAttack is query efficient and can break models for both targeted and non-targeted attacks. PatchAttack induces misclassifications by superimposing small textured patches on the input image. We parametrize the appearance of these patches by a dictionary of class-specific textures. This texture dictionary is learned by clustering Gram matrices of feature activations from a VGG backbone. PatchAttack optimizes the position and texture parameters of each patch using reinforcement learning. Our experiments show that PatchAttack achieves > 99% success rate on ImageNet for a wide range of architectures, while only manipulating 3% of the image for non-targeted attacks and 10% on average for targeted attacks. Furthermore, we show that PatchAttack circumvents state-of-the-art adversarial defense methods successfully. T
more »
« less
- Award ID(s):
- 1827427
- PAR ID:
- 10205506
- Date Published:
- Journal Name:
- European Conference on Computer Vision (ECCV) 2020
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The benefits of utilizing spatial context in fast object detection algorithms have been studied extensively. Detectors increase inference speed by doing a single forward pass per image which means they implicitly use contextual reasoning for their predictions. However, one can show that an adversary can design adversarial patches which do not overlap with any objects of interest in the scene and exploit con- textual reasoning to fool standard detectors. In this paper, we examine this problem and design category specific adversarial patches which make a widely used object detector like YOLO blind to an attacker chosen object category. We also show that limiting the use of spatial context during object detector training improves robustness to such adversaries. We believe the existence of context based adversarial attacks is concerning since the adversarial patch can affect predictions without being in vicinity of any objects of interest. Hence, defending against such attacks becomes challenging and we urge the research community to give attention to this vulnerability.more » « less
-
Cloud detection is an inextricable pre-processing step in remote sensing image analysis workflows. Most of the traditional rule-based and machine-learning-based algorithms utilize low-level features of the clouds and classify individual cloud pixels based on their spectral signatures. Cloud detection using such approaches can be challenging due to a multitude of factors including harsh lighting conditions, the presence of thin clouds, the context of surrounding pixels, and complex spatial patterns. In recent studies, deep convolutional neural networks (CNNs) have shown outstanding results in the computer vision domain. These methods are practiced for better capturing the texture, shape as well as context of images. In this study, we propose a deep learning CNN approach to detect cloud pixels from medium-resolution satellite imagery. The proposed CNN accounts for both the low-level features, such as color and texture information as well as high-level features extracted from successive convolutions of the input image. We prepared a cloud-pixel dataset of approximately 7273 randomly sampled 320 by 320 pixels image patches taken from a total of 121 Landsat-8 (30m) and Sentinel-2 (20m) image scenes. These satellite images come with cloud masks. From the available data channels, only blue, green, red, and NIR bands are fed into the model. The CNN model was trained on 5300 image patches and validated on 1973 independent image patches. As the final output from our model, we extract a binary mask of cloud pixels and non-cloud pixels. The results are benchmarked against established cloud detection methods using standard accuracy metrics.more » « less
-
Vision transformers (ViTs) have recently set off a new wave in neural architecture design thanks to their record-breaking performance in various vision tasks. In parallel, to fulfill the goal of deploying ViTs into real-world vision applications, their robustness against potential malicious attacks has gained increasing attention. In particular, recent works show that ViTs are more robust against adversarial attacks as compared with convolutional neural networks (CNNs), and conjecture that this is because ViTs focus more on capturing global interactions among different input/feature patches, leading to their improved robustness to local perturbations imposed by adversarial attacks. In this work, we ask an intriguing question: “Under what kinds of perturbations do ViTs become more vulnerable learners compared to CNNs?” Driven by this question, we first conduct a comprehensive experiment regarding the robustness of both ViTs and CNNs under various existing adversarial attacks to understand the underlying reason favoring their robustness. Based on the drawn insights, we then propose a dedicated attack framework, dubbed Patch-Fool, that fools the self-attention mechanism by attacking its basic component (i.e., a single patch) with a series of attention-aware optimization techniques. Interestingly, our Patch-Fool framework shows for the first time that ViTs are not necessarily more robust than CNNs against adversarial perturbations. In particular, we find that ViTs are more vulnerable learners compared with CNNs against our Patch-Fool attack which is consistent across extensive experiments, and the observations from Sparse/Mild Patch-Fool, two variants of Patch-Fool, indicate an intriguing insight that the perturbation density and strength on each patch seem to be the key factors that influence the robustness ranking between ViTs and CNNs. It can be expected that our Patch-Fool framework will shed light on both future architecture designs and training schemes for robustifying ViTs towards their real-world deployment. Our codes are available at https://github.com/RICE-EIC/Patch-Fool.more » « less
-
null (Ed.)Patch adversarial attacks on images, in which the attacker can distort pixels within a region of bounded size, are an important threat model since they provide a quantitative model for physical adversarial attacks. In this paper, we introduce a certifiable defense against patch attacks that guarantees for a given image and patch attack size, no patch adversarial examples exist. Our method is related to the broad class of randomized smoothing robustness schemes which provide high-confidence probabilistic robustness certificates. By exploiting the fact that patch attacks are more constrained than general sparse attacks, we derive meaningfully large robustness certificates against them. Additionally, in contrast to smoothing-based defenses against L_p and sparse attacks, our defense method against patch attacks is de-randomized, yielding improved, deterministic certificates. Compared to the existing patch certification method proposed by Chiang et al. (2020), which relies on interval bound propagation, our method can be trained significantly faster, achieves high clean and certified robust accuracy on CIFAR-10, and provides certificates at ImageNet scale. For example, for a 5-by-5 patch attack on CIFAR-10, our method achieves up to around 57.6% certified accuracy (with a classifier with around 83.8% clean accuracy), compared to at most 30.3% certified accuracy for the existing method (with a classifier with around 47.8% clean accuracy). Our results effectively establish a new state-of-the-art of certifiable defense against patch attacks on CIFAR-10 and ImageNet.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1007/978-3-030-58574-7_41
