Sheng Zhong

Ying He, Zhili Shen, Chang Xia et al.

Outsourced deep neural networks have been demonstrated to suffer from patch-based trojan attacks, in which an adversary poisons the training sets to inject a backdoor in the obtained model so that regular inputs can be still labeled correctly while those carrying a specific trigger are falsely given a target label. Due to the severity of such attacks, many backdoor detection and containment systems have recently, been proposed for deep neural networks. One major category among them are various model inspection schemes, which hope to detect backdoors before deploying models from non-trusted third-parties. In this paper, we show that such state-of-the-art schemes can be defeated by a so-called Scapegoat Backdoor Attack, which introduces a benign scapegoat trigger in data poisoning to prevent the defender from reversing the real abnormal trigger. In addition, it confines the values of network parameters within the same variances of those from clean model during training, which further significantly enhances the difficulty of the defender to learn the differences between legal and illegal models through machine-learning approaches. Our experiments on 3 popular datasets show that it can escape detection by all five state-of-the-art model inspection schemes. Moreover, this attack brings almost no side-effects on the attack effectiveness and guarantees the universal feature of the trigger compared with original patch-based trojan attacks.

Shucheng Li, Lingfei Wu, Shiwei Feng et al.

The celebrated Seq2Seq technique and its numerous variants achieve excellent performance on many tasks such as neural machine translation, semantic parsing, and math word problem solving. However, these models either only consider input objects as sequences while ignoring the important structural information for encoding, or they simply treat output objects as sequence outputs instead of structural objects for decoding. In this paper, we present a novel Graph-to-Tree Neural Networks, namely Graph2Tree consisting of a graph encoder and a hierarchical tree decoder, that encodes an augmented graph-structured input and decodes a tree-structured output. In particular, we investigated our model for solving two problems, neural semantic parsing and math word problem. Our extensive experiments demonstrate that our Graph2Tree model outperforms or matches the performance of other state-of-the-art models on these tasks.

Sheng Zhong, Shifu Zhou

Natural images can be regarded as residing in a manifold that is embedded in a higher dimensional Euclidean space. Generative Adversarial Networks (GANs) try to learn the distribution of the real images in the manifold to generate samples that look real. But the results of existing methods still exhibit many unpleasant artifacts and distortions even for the cases where the desired ground truth target images are available for supervised learning such as in single image super resolution (SISR). We probe for ways to alleviate these problems for supervised GANs in this paper. We explicitly apply the Lipschitz Continuity Condition (LCC) to regularize the GAN. An encoding network that maps the image space to a new optimal latent space is derived from the LCC, and it is used to augment the GAN as a coupling component. The LCC is also converted to new regularization terms in the generator loss function to enforce local invariance. The GAN is optimized together with the encoding network in an attempt to make the generator converge to a more ideal and disentangled mapping that can generate samples more faithful to the target images. When the proposed models are applied to the single image super resolution problem, the results outperform the state of the art.

Qingjun Chen, Chen Qian, Sheng Zhong

Today's large-scale enterprise networks, data center networks, and wide area networks can be decomposed into multiple administrative or geographical domains. Domains may be owned by different administrative units or organizations. Hence protecting domain information is an important concern. Existing general-purpose Secure Multi-Party Computation (SMPC) methods that preserves privacy for domains are extremely slow for cross-domain routing problems. In this paper we present PYCRO, a cryptographic protocol specifically designed for privacy-preserving cross-domain routing optimization in Software Defined Networking (SDN) environments. PYCRO provides two fundamental routing functions, policy-compliant shortest path computing and bandwidth allocation, while ensuring strong protection for the private information of domains. We rigorously prove the privacy guarantee of our protocol. We have implemented a prototype system that runs PYCRO on servers in a campus network. Experimental results using real ISP network topologies show that PYCRO is very efficient in computation and communication costs.

Jingyu Hua, Zhenyu Shen, Sheng Zhong

Motion sensors (e.g., accelerometers) on smartphones have been demonstrated to be a powerful side channel for attackers to spy on users' inputs on touchscreen. In this paper, we reveal another motion accelerometer-based attack which is particularly serious: when a person takes the metro, a malicious application on her smartphone can easily use accelerator readings to trace her. We first propose a basic attack that can automatically extract metro-related data from a large amount of mixed accelerator readings, and then use an ensemble interval classier built from supervised learning to infer the riding intervals of the user. While this attack is very effective, the supervised learning part requires the attacker to collect labeled training data for each station interval, which is a significant amount of effort. To improve the efficiency of our attack, we further propose a semi-supervised learning approach, which only requires the attacker to collect labeled data for a very small number of station intervals with obvious characteristics. We conduct real experiments on a metro line in a major city. The results show that the inferring accuracy could reach 89\% and 92\% if the user takes the metro for 4 and 6 stations, respectively.