The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform
Jia Wang - One of the best experts on this subject based on the ideXlab platform.
-
The taming of the shrew: mitigating low-rate TCP-Targeted Attack
IEEE Transactions on Network and Service Management, 2010Co-Authors: Chia-wei Chang, Jia WangAbstract:A Shrew Attack, which uses a low-rate burst carefully designed to exploit TCP's retransmission timeout mechanism, can throttle the bandwidth of a TCP flow in a stealthy manner. While such an Attack can significantly degrade the performance of all TCP-based protocols and services including Internet routing (e.g., BGP), no existing scheme clearly solves the problem in real network scenarios. In this paper, we propose a simple protection mechanism, called SAP (Shrew Attack Protection), for defending against a Shrew Attack. Rather than attempting to track and isolate Shrew Attackers, SAP identifies TCP victims by monitoring their drop rates and preferentially admits those packets from the victims with high drop rates to the output queue. This is to ensure that well-behaved TCP sessions can retain their bandwidth shares. Our simulation results indicate that under a Shrew Attack, SAP can prevent TCP sessions from closing, and effectively enable TCP flows to maintain high throughput. SAP is a destination-port-based mechanism and requires only a small number of counters to find potential victims, which makes SAP readily implementable on top of existing router mechanisms.
-
The Taming of the Shrew: Mitigating Low-Rate TCP-Targeted Attack
2009 29th IEEE International Conference on Distributed Computing Systems, 2009Co-Authors: Chia-wei Chang, Jia WangAbstract:A Shrew Attack, which uses a low-rate burst carefully designed to exploit TCP's retransmission timeout mechanism, can throttle the bandwidth of a TCP flow in a stealthy manner. While such an Attack can significantly degrade the performance of all TCP-based protocols and services including Internet routing (e.g., BGP), no existing scheme clearly solves the problem in real network scenarios. In this paper, we propose a simple protection mechanism, called SAP (Shrew Attack Protection), for defending against a Shrew Attack. Rather than attempting to track and isolate Shrew Attackers, SAP identifies TCP victims by monitoring their drop rates and preferentially admits those packets from victims with high drop rates to the output queue. This is to ensure that well-behaved TCP sessions can retain their bandwidth shares. Our simulations indicate that under a Shrew Attack, SAP can prevent TCP sessions from closing, and effectively enable TCP flows to maintain high throughput. SAP is a destination-port-based mechanism and requires only a small number of counters to find potential victims, which makes SAP readily implementable on top of existing router mechanisms.
Chia-wei Chang - One of the best experts on this subject based on the ideXlab platform.
-
The taming of the shrew: mitigating low-rate TCP-Targeted Attack
IEEE Transactions on Network and Service Management, 2010Co-Authors: Chia-wei Chang, Jia WangAbstract:A Shrew Attack, which uses a low-rate burst carefully designed to exploit TCP's retransmission timeout mechanism, can throttle the bandwidth of a TCP flow in a stealthy manner. While such an Attack can significantly degrade the performance of all TCP-based protocols and services including Internet routing (e.g., BGP), no existing scheme clearly solves the problem in real network scenarios. In this paper, we propose a simple protection mechanism, called SAP (Shrew Attack Protection), for defending against a Shrew Attack. Rather than attempting to track and isolate Shrew Attackers, SAP identifies TCP victims by monitoring their drop rates and preferentially admits those packets from the victims with high drop rates to the output queue. This is to ensure that well-behaved TCP sessions can retain their bandwidth shares. Our simulation results indicate that under a Shrew Attack, SAP can prevent TCP sessions from closing, and effectively enable TCP flows to maintain high throughput. SAP is a destination-port-based mechanism and requires only a small number of counters to find potential victims, which makes SAP readily implementable on top of existing router mechanisms.
-
The Taming of the Shrew: Mitigating Low-Rate TCP-Targeted Attack
2009 29th IEEE International Conference on Distributed Computing Systems, 2009Co-Authors: Chia-wei Chang, Jia WangAbstract:A Shrew Attack, which uses a low-rate burst carefully designed to exploit TCP's retransmission timeout mechanism, can throttle the bandwidth of a TCP flow in a stealthy manner. While such an Attack can significantly degrade the performance of all TCP-based protocols and services including Internet routing (e.g., BGP), no existing scheme clearly solves the problem in real network scenarios. In this paper, we propose a simple protection mechanism, called SAP (Shrew Attack Protection), for defending against a Shrew Attack. Rather than attempting to track and isolate Shrew Attackers, SAP identifies TCP victims by monitoring their drop rates and preferentially admits those packets from victims with high drop rates to the output queue. This is to ensure that well-behaved TCP sessions can retain their bandwidth shares. Our simulations indicate that under a Shrew Attack, SAP can prevent TCP sessions from closing, and effectively enable TCP flows to maintain high throughput. SAP is a destination-port-based mechanism and requires only a small number of counters to find potential victims, which makes SAP readily implementable on top of existing router mechanisms.
Zheng Zhang - One of the best experts on this subject based on the ideXlab platform.
-
Targeted Attack of deep hashing via prototype supervised adversarial networks
IEEE Transactions on Multimedia, 2021Co-Authors: Zheng Zhang, Xunguang Wang, Fumin Shen, Lei ZhuAbstract:Due to its powerful capability of representation learning and high-efficiency computation, deep hashing has made significant progress in large-scale image retrieval. It has been recognized that deep neural networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in deep hashing-based retrieval field. In this paper, we propose a novel prototype-supervised adversarial network (ProS-GAN), which formulates a flexible generative architecture for efficient and effective Targeted hashing Attack. To the best of our knowledge, this is one of the first generation-based methods to Attack deep hashing networks. Generally, our proposed framework consists of three parts, i.e., a PrototypeNet, a Generator and a Discriminator. Specifically, the designed PrototypeNet embeds the target label into the semantic representation and learns the prototype code as the category-level representative of the target label. Moreover, the semantic representation and the original image are jointly fed into the generator for flexible Targeted Attack. Particularly, the prototype code is adopted to supervise the generator to construct the Targeted adversarial example by minimizing the Hamming distance between the hash code of the adversarial example and the prototype code. Furthermore, the generator fools the discriminator to simultaneously encourage the adversarial examples visually realistic and the semantic representation informative. Extensive experiments demonstrate that the proposed framework can efficiently produce adversarial examples with better Targeted Attack performance and transferability over state-of-the-art Targeted Attack methods of deep hashing.
-
Targeted Attack and defense for deep hashing
International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021Co-Authors: Xunguang Wang, Zheng ZhangAbstract:Deep hashing methods have been intensively studied and successfully applied in massive fast image retrieval. However, inherited from the deficiency of deep neural networks, deep hashing models can be easily fooled by adversarial examples, which brings a serious security risk to hashing based retrieval. In this paper, we propose a novel Targeted Attack method and the first defense scheme for deep hashing based retrieval. Specifically, a simple yet effective PrototypeNet is designed to generate category-level semantic embedding (dubbed prototype code) regarded as the semantic representative of the target label, which preserves the semantic similarity with relevant labels and dissimilarity with irrelevant labels. Subsequently, we conduct the Targeted Attack by minimizing the Hamming distance between the hash code of the adversarial sample and the prototype code. Moreover, we provide an adversarial training algorithm to improve the adversarial robustness of deep hashing networks. Extensive experiments demonstrate our method can produce high-quality adversarial samples with the benefit of superior Targeted Attack performance over state-of-the-arts. Importantly, our adversarial defense framework can significantly boost the robustness of hashing networks against adversarial Attacks on deep hashing based retrieval. The code is available at https://github.com/xunguangwang/Targeted-Attack-and-Defense-for-Deep-Hashing.
-
prototype supervised adversarial network for Targeted Attack of deep hashing
Computer Vision and Pattern Recognition, 2021Co-Authors: Xunguang Wang, Zheng Zhang, Fumin ShenAbstract:Due to its powerful capability of representation learning and high-efficiency computation, deep hashing has made significant progress in large-scale image retrieval. However, deep hashing networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in hashing-based retrieval field. In this paper, we propose a novel prototype-supervised adversarial network (ProS-GAN), which formulates a flexible generative architecture for efficient and effective Targeted hashing Attack. To the best of our knowledge, this is the first generation-based method to Attack deep hashing networks. Generally, our proposed framework consists of three parts, i.e., a PrototypeNet, a generator and a discriminator. Specifically, the designed PrototypeNet embeds the target label into the semantic representation and learns the prototype code as the category-level representative of the target label. Moreover, the semantic representation and the original image are jointly fed into the generator for flexible Targeted Attack. Particularly, the prototype code is adopted to supervise the generator to construct the Targeted adversarial example by minimizing the Hamming distance between the hash code of the adversarial example and the prototype code. Furthermore, the generator is against the discriminator to simultaneously encourage the adversarial examples visually realistic and the semantic representation informative. Extensive experiments verify that the proposed framework can efficiently produce adversarial examples with better Targeted Attack performance and transferability over state-of-the-art Targeted Attack methods of deep hashing.
-
prototype supervised adversarial network for Targeted Attack of deep hashing
arXiv: Computer Vision and Pattern Recognition, 2021Co-Authors: Xunguang Wang, Zheng Zhang, Fumin ShenAbstract:Due to its powerful capability of representation learning and high-efficiency computation, deep hashing has made significant progress in large-scale image retrieval. However, deep hashing networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in hashing-based retrieval field. In this paper, we propose a novel prototype-supervised adversarial network (ProS-GAN), which formulates a flexible generative architecture for efficient and effective Targeted hashing Attack. To the best of our knowledge, this is the first generation-based method to Attack deep hashing networks. Generally, our proposed framework consists of three parts, i.e., a PrototypeNet, a generator, and a discriminator. Specifically, the designed PrototypeNet embeds the target label into the semantic representation and learns the prototype code as the category-level representative of the target label. Moreover, the semantic representation and the original image are jointly fed into the generator for a flexible Targeted Attack. Particularly, the prototype code is adopted to supervise the generator to construct the Targeted adversarial example by minimizing the Hamming distance between the hash code of the adversarial example and the prototype code. Furthermore, the generator is against the discriminator to simultaneously encourage the adversarial examples visually realistic and the semantic representation informative. Extensive experiments verify that the proposed framework can efficiently produce adversarial examples with better Targeted Attack performance and transferability over state-of-the-art Targeted Attack methods of deep hashing. The related codes could be available at this https URL .
Xunguang Wang - One of the best experts on this subject based on the ideXlab platform.
-
Targeted Attack of deep hashing via prototype supervised adversarial networks
IEEE Transactions on Multimedia, 2021Co-Authors: Zheng Zhang, Xunguang Wang, Fumin Shen, Lei ZhuAbstract:Due to its powerful capability of representation learning and high-efficiency computation, deep hashing has made significant progress in large-scale image retrieval. It has been recognized that deep neural networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in deep hashing-based retrieval field. In this paper, we propose a novel prototype-supervised adversarial network (ProS-GAN), which formulates a flexible generative architecture for efficient and effective Targeted hashing Attack. To the best of our knowledge, this is one of the first generation-based methods to Attack deep hashing networks. Generally, our proposed framework consists of three parts, i.e., a PrototypeNet, a Generator and a Discriminator. Specifically, the designed PrototypeNet embeds the target label into the semantic representation and learns the prototype code as the category-level representative of the target label. Moreover, the semantic representation and the original image are jointly fed into the generator for flexible Targeted Attack. Particularly, the prototype code is adopted to supervise the generator to construct the Targeted adversarial example by minimizing the Hamming distance between the hash code of the adversarial example and the prototype code. Furthermore, the generator fools the discriminator to simultaneously encourage the adversarial examples visually realistic and the semantic representation informative. Extensive experiments demonstrate that the proposed framework can efficiently produce adversarial examples with better Targeted Attack performance and transferability over state-of-the-art Targeted Attack methods of deep hashing.
-
Targeted Attack and defense for deep hashing
International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021Co-Authors: Xunguang Wang, Zheng ZhangAbstract:Deep hashing methods have been intensively studied and successfully applied in massive fast image retrieval. However, inherited from the deficiency of deep neural networks, deep hashing models can be easily fooled by adversarial examples, which brings a serious security risk to hashing based retrieval. In this paper, we propose a novel Targeted Attack method and the first defense scheme for deep hashing based retrieval. Specifically, a simple yet effective PrototypeNet is designed to generate category-level semantic embedding (dubbed prototype code) regarded as the semantic representative of the target label, which preserves the semantic similarity with relevant labels and dissimilarity with irrelevant labels. Subsequently, we conduct the Targeted Attack by minimizing the Hamming distance between the hash code of the adversarial sample and the prototype code. Moreover, we provide an adversarial training algorithm to improve the adversarial robustness of deep hashing networks. Extensive experiments demonstrate our method can produce high-quality adversarial samples with the benefit of superior Targeted Attack performance over state-of-the-arts. Importantly, our adversarial defense framework can significantly boost the robustness of hashing networks against adversarial Attacks on deep hashing based retrieval. The code is available at https://github.com/xunguangwang/Targeted-Attack-and-Defense-for-Deep-Hashing.
-
prototype supervised adversarial network for Targeted Attack of deep hashing
Computer Vision and Pattern Recognition, 2021Co-Authors: Xunguang Wang, Zheng Zhang, Fumin ShenAbstract:Due to its powerful capability of representation learning and high-efficiency computation, deep hashing has made significant progress in large-scale image retrieval. However, deep hashing networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in hashing-based retrieval field. In this paper, we propose a novel prototype-supervised adversarial network (ProS-GAN), which formulates a flexible generative architecture for efficient and effective Targeted hashing Attack. To the best of our knowledge, this is the first generation-based method to Attack deep hashing networks. Generally, our proposed framework consists of three parts, i.e., a PrototypeNet, a generator and a discriminator. Specifically, the designed PrototypeNet embeds the target label into the semantic representation and learns the prototype code as the category-level representative of the target label. Moreover, the semantic representation and the original image are jointly fed into the generator for flexible Targeted Attack. Particularly, the prototype code is adopted to supervise the generator to construct the Targeted adversarial example by minimizing the Hamming distance between the hash code of the adversarial example and the prototype code. Furthermore, the generator is against the discriminator to simultaneously encourage the adversarial examples visually realistic and the semantic representation informative. Extensive experiments verify that the proposed framework can efficiently produce adversarial examples with better Targeted Attack performance and transferability over state-of-the-art Targeted Attack methods of deep hashing.
-
prototype supervised adversarial network for Targeted Attack of deep hashing
arXiv: Computer Vision and Pattern Recognition, 2021Co-Authors: Xunguang Wang, Zheng Zhang, Fumin ShenAbstract:Due to its powerful capability of representation learning and high-efficiency computation, deep hashing has made significant progress in large-scale image retrieval. However, deep hashing networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in hashing-based retrieval field. In this paper, we propose a novel prototype-supervised adversarial network (ProS-GAN), which formulates a flexible generative architecture for efficient and effective Targeted hashing Attack. To the best of our knowledge, this is the first generation-based method to Attack deep hashing networks. Generally, our proposed framework consists of three parts, i.e., a PrototypeNet, a generator, and a discriminator. Specifically, the designed PrototypeNet embeds the target label into the semantic representation and learns the prototype code as the category-level representative of the target label. Moreover, the semantic representation and the original image are jointly fed into the generator for a flexible Targeted Attack. Particularly, the prototype code is adopted to supervise the generator to construct the Targeted adversarial example by minimizing the Hamming distance between the hash code of the adversarial example and the prototype code. Furthermore, the generator is against the discriminator to simultaneously encourage the adversarial examples visually realistic and the semantic representation informative. Extensive experiments verify that the proposed framework can efficiently produce adversarial examples with better Targeted Attack performance and transferability over state-of-the-art Targeted Attack methods of deep hashing. The related codes could be available at this https URL .
Shlomo Havlin - One of the best experts on this subject based on the ideXlab platform.
-
percolation of localized Attack on complex networks
New Journal of Physics, 2015Co-Authors: Shuai Shao, Shlomo Havlin, Xuqing Huang, Eugene H StanleyAbstract:The robustness of complex networks against node failure and malicious Attack has been of interest for decades, while most of the research has focused on random Attack or hub-Targeted Attack. In many real-world scenarios, however, Attacks are neither random nor hub-Targeted, but localized, where a group of neighboring nodes in a network are Attacked and fail. In this paper we develop a percolation framework to analytically and numerically study the robustness of complex networks against such localized Attack. In particular, we investigate this robustness in Erd?s?R?nyi networks, random-regular networks, and scale-free networks. Our results provide insight into how to better protect networks, enhance cybersecurity, and facilitate the design of more robust infrastructures.
-
percolation of localized Attack on complex networks
arXiv: Physics and Society, 2014Co-Authors: Shuai Shao, Shlomo Havlin, Xuqing Huang, Eugene H StanleyAbstract:The robustness of complex networks against node failure and malicious Attack has been of interest for decades, while most of the research has focused on random Attack or hub-Targeted Attack. In many real-world scenarios, however, Attacks are neither random nor hub-Targeted, but localized, where a group of neighboring nodes in a network are Attacked and fail. In this paper we develop a percolation framework to analytically and numerically study the robustness of complex networks against such localized Attack. In particular, we investigate this robustness in Erd\H{o}s-R\'{e}nyi networks, random-regular networks, and scale-free networks. Our results provide insight into how to better protect networks, enhance cybersecurity, and facilitate the design of more robust infrastructures.
-
robustness of network of networks under Targeted Attack
Physical Review E, 2013Co-Authors: Gaogao Dong, Eugene H Stanley, Jianxi Gao, Lixin Tian, Shlomo HavlinAbstract:The robustness of a network of networks (NON) under random Attack has been studied recently [Gao et al., Phys. Rev. Lett. 107, 195701 (2011)]. Understanding how robust a NON is to Targeted Attacks is a major challenge when designing resilient infrastructures. We address here the question how the robustness of a NON is affected by Targeted Attack on high- or low-degree nodes. We introduce a Targeted Attack probability function that is dependent upon node degree and study the robustness of two types of NON under Targeted Attack: (i) a tree of n fully interdependent Erdős-Renyi or scale-free networks and (ii) a starlike network of n partially interdependent Erdős-Renyi networks. For any tree of n fully interdependent Erdős-Renyi networks and scale-free networks under Targeted Attack, we find that the network becomes significantly more vulnerable when nodes of higher degree have higher probability to fail. When the probability that a node will fail is proportional to its degree, for a NON composed of Erdős-Renyi networks we find analytical solutions for the mutual giant component P(∞) as a function of p, where 1-p is the initial fraction of failed nodes in each network. We also find analytical solutions for the critical fraction p(c), which causes the fragmentation of the n interdependent networks, and for the minimum average degree k[over ¯](min) below which the NON will collapse even if only a single node fails. For a starlike NON of n partially interdependent Erdős-Renyi networks under Targeted Attack, we find the critical coupling strength q(c) for different n. When q>q(c), the Attacked system undergoes an abrupt first order type transition. When q≤q(c), the system displays a smooth second order percolation transition. We also evaluate how the central network becomes more vulnerable as the number of networks with the same coupling strength q increases. The limit of q=0 represents no dependency, and the results are consistent with the classical percolation theory of a single network under Targeted Attack.
-
robustness of interdependent networks under Targeted Attack
Bulletin of the American Physical Society, 2012Co-Authors: Xuqing Huang, Shlomo Havlin, Jianxi Gao, Sergey V Buldyrev, Eugene H StanleyAbstract:When an initial failure of nodes occurs in interdependent networks, a cascade of failure between the networks occurs. Earlier studies focused on random initial failures. Here we study the robustness of interdependent networks under Targeted Attack on high or low degree nodes. We introduce a general technique which maps the Targeted-Attack problem in interdependent networks to the random-Attack problem in a transformed pair of interdependent networks. We find that when the highly connected nodes are protected and have lower probability to fail, in contrast to single scale-free (SF) networks where the percolation threshold pc = 0, coupled SF networks are significantly more vulnerable with pc significantly larger than zero. The result implies that interdependent networks are difficult to defend by strategies such as protecting the high degree nodes that have been found useful to significantly improve robustness of single networks.
