More Like this

1. Adversarial Attack on Graph Structured Data

   Dai, Hanjun; Li, Hui; Tian, Tian; Huang, Xin; Wang, Lin; Zhu, Jun; Song, Le (July 2018, Proceedings of the 35th International Conference on Machine Learning, PMLR)

   Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and defense. In this paper, we focus on the adversarial attacks that fool deep learning models by modifying the combinatorial structure of data. We first propose a reinforcement learning based attack method that learns the generalizable attack policy, while only requiring prediction labels from the target classifier. We further propose attack methods based on genetic algorithms and gradient descent in the scenario where additional prediction confidence or gradients are available. We use both synthetic and real-world data to show that, a family of Graph Neural Network models are vulnerable to these attacks, in both graph-level and node-level classification tasks. We also show such attacks can be used to diagnose the learned classifiers. 

   more » « less
2. Adversarial Attacks on Graph Neural Networks via Node Injections: A Hierarchical Reinforcement Learning Approach

   https://doi.org/10.1145/3366423.3380149  

   Sun, Yiwei; Wang, Suhang; Tang, Xianfeng; Hsieh, Tsung-Yu; Honavar, Vasant G. (January 2020, Proceedings of The Web Conference 2020 (WWW '20))

   Graph Neural Networks (GNN) offer the powerful approach to node classification in complex networks across many domains including social media, E-commerce, and FinTech. However, recent studies show that GNNs are vulnerable to attacks aimed at adversely impacting their node classification performance. Existing studies of adversarial attacks on GNN focus primarily on manipulating the connectivity between existing nodes, a task that requires greater effort on the part of the attacker in real-world applications. In contrast, it is much more expedient on the part of the attacker to inject adversarial nodes, e.g., fake profiles with forged links, into existing graphs so as to reduce the performance of the GNN in classifying existing nodes. Hence, we consider a novel form of node injection poisoning attacks on graph data. We model the key steps of a node injection attack, e.g., establishing links between the injected adversarial nodes and other nodes, choosing the label of an injected node, etc. by a Markov Decision Process. We propose a novel reinforcement learning method for Node Injection Poisoning Attacks (NIPA), to sequentially modify the labels and links of the injected nodes, without changing the connectivity between existing nodes. Specifically, we introduce a hierarchical Q-learning network to manipulate the labels of the adversarial nodes and their links with other nodes in the graph, and design an appropriate reward function to guide the reinforcement learning agent to reduce the node classification performance of GNN. The results of the experiments show that NIPA is consistently more effective than the baseline node injection attack methods for poisoning graph data on three benchmark datasets. 

   more » « less
3. Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks

   Lin, Wei-An; Pong Lau, Chun; Levine, Alexander; Chellappa, Rama; Feizi, Soheil (January 2020, Advances in Neural Information Processing Systems Foundation (NeurIPS))

   null (Ed.)

   Adversarial training is a popular defense strategy against attack threat models with bounded Lp norms. However, it often degrades the model performance on normal images and the defense does not generalize well to novel attacks. Given the success of deep generative models such as GANs and VAEs in characterizing the underlying manifold of images, we investigate whether or not the aforementioned problems can be remedied by exploiting the underlying manifold information. To this end, we construct an "On-Manifold ImageNet" (OM-ImageNet) dataset by projecting the ImageNet samples onto the manifold learned by StyleGSN. For this dataset, the underlying manifold information is exact. Using OM-ImageNet, we first show that adversarial training in the latent space of images improves both standard accuracy and robustness to on-manifold attacks. However, since no out-of-manifold perturbations are realized, the defense can be broken by Lp adversarial attacks. We further propose Dual Manifold Adversarial Training (DMAT) where adversarial perturbations in both latent and image spaces are used in robustifying the model. Our DMAT improves performance on normal images, and achieves comparable robustness to the standard adversarial training against Lp attacks. In addition, we observe that models defended by DMAT achieve improved robustness against novel attacks which manipulate images by global color shifts or various types of image filtering. Interestingly, similar improvements are also achieved when the defended models are tested on out-of-manifold natural images. These results demonstrate the potential benefits of using manifold information in enhancing robustness of deep learning models against various types of novel adversarial attacks. 

   more » « less
4. Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks

   Jin, Hongwei; Shi, Zhan; Peruri, Ashish; Zhang, Xinhua (January 2020, Advances in neural information processing systems)

   null (Ed.)

   Graph convolution networks (GCNs) have become effective models for graph classification. Similar to many deep networks, GCNs are vulnerable to adversarial attacks on graph topology and node attributes. Recently, a number of effective attack and defense algorithms have been designed, but no certificate of robustness has been developed for GCN-based graph classification under topological perturbations with both local and global budgets. In this paper, we propose the first certificate for this problem. Our method is based on Lagrange dualization and convex envelope, which result in tight approximation bounds that are efficiently computable by dynamic programming. When used in conjunction with robust training, it allows an increased number of graphs to be certified as robust. 

   more » « less
5. Physical Adversarial Examples for Object Detectors

   Eykholt, Kevin; Evtimov, Ivan; Fernandes, Earlence; Li, Bo; Rahmati, Amir; Tramer, Florian; Prakash, Atul; Kohno, Tadayoshi; Song, Dawn (August 2018, 12th USENIX Workshop on Offensive Technologies (WOOT 18))

   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