no code implementations • 2 Mar 2024 • Jiacen Xu, Jack W. Stokes, Geoff McDonald, Xuesong Bai, David Marshall, Siyue Wang, Adith Swaminathan, Zhou Li
Large language models (LLMs) have demonstrated impressive results on natural language tasks, and security researchers are beginning to employ them in both offensive and defensive systems.
no code implementations • 30 Jan 2024 • Chenan Wang, Pu Zhao, Siyue Wang, Xue Lin
Deep Neural Network (DNN) models when implemented on executing devices as the inference engines are susceptible to Fault Injection Attacks (FIAs) that manipulate model parameters to disrupt inference execution with disastrous performance.
no code implementations • 27 Mar 2023 • Ruyi Ding, Cheng Gongye, Siyue Wang, Aidong Ding, Yunsi Fei
Inspired by the fact that electromagnetic (EM) emanations of a model inference are dependent on both operations and data and may contain footprints of different input classes, we propose a framework, EMShepherd, to capture EM traces of model execution, perform processing on traces and exploit them for adversarial detection.
1 code implementation • 26 Apr 2022 • Siyue Wang, Giles R. S. Atkinson, Wayne B. Hayes
We argue that this failure of topology alone is due to the sparsity and incompleteness of the PPI network data of almost all species, which provides the network topology with a small signal-to-noise ratio that is effectively swamped when sequence information is added to the mix.
1 code implementation • 25 Apr 2022 • Siyue Wang, Xiaoyin Chen, Brent J. Frederisy, Benedict A. Mbakogu, Amy D. Kanne, Pasha Khosravi, Wayne B. Hayes
The function of a protein is defined by its interaction partners.
1 code implementation • NeurIPS 2021 • Geng Yuan, Xiaolong Ma, Wei Niu, Zhengang Li, Zhenglun Kong, Ning Liu, Yifan Gong, Zheng Zhan, Chaoyang He, Qing Jin, Siyue Wang, Minghai Qin, Bin Ren, Yanzhi Wang, Sijia Liu, Xue Lin
Systematical evaluation on accuracy, training speed, and memory footprint are conducted, where the proposed MEST framework consistently outperforms representative SOTA works.
no code implementations • 14 May 2021 • Siyue Wang, Xiao Wang, Pin-Yu Chen, Pu Zhao, Xue Lin
This paper proposes Characteristic Examples for effectively fingerprinting deep neural networks, featuring high-robustness to the base model against model pruning as well as low-transferability to unassociated models.
no code implementations • 19 Feb 2020 • Peiyan Dong, Siyue Wang, Wei Niu, Chengming Zhang, Sheng Lin, Zhengang Li, Yifan Gong, Bin Ren, Xue Lin, Yanzhi Wang, Dingwen Tao
Recurrent neural networks (RNNs) based automatic speech recognition has nowadays become prevalent on mobile devices such as smart phones.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 19 Feb 2020 • Xiao Wang, Siyue Wang, Pin-Yu Chen, Xue Lin, Peter Chin
Designing effective defense against adversarial attacks is a crucial topic as deep neural networks have been proliferated rapidly in many security-critical domains such as malware detection and self-driving cars.
1 code implementation • 18 Feb 2020 • Pu Zhao, Pin-Yu Chen, Siyue Wang, Xue Lin
Despite the great achievements of the modern deep neural networks (DNNs), the vulnerability/robustness of state-of-the-art DNNs raises security concerns in many application domains requiring high reliability.
no code implementations • 18 Feb 2020 • Xiao Wang, Siyue Wang, Pin-Yu Chen, Xue Lin, Peter Chin
Recent study of adversarial attacks has revealed the vulnerability of modern deep learning models.
1 code implementation • 20 Aug 2019 • Xiao Wang, Siyue Wang, Pin-Yu Chen, Yanzhi Wang, Brian Kulis, Xue Lin, Peter Chin
However, one critical drawback of current defenses is that the robustness enhancement is at the cost of noticeable performance degradation on legitimate data, e. g., large drop in test accuracy.
no code implementations • 28 May 2019 • Pu Zhao, Siyue Wang, Cheng Gongye, Yanzhi Wang, Yunsi Fei, Xue Lin
Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability. We propose the fault sneaking attack on DNNs, where the adversary aims to misclassify certain input images into any target labels by modifying the DNN parameters.
no code implementations • 12 Dec 2018 • Zhe Li, Caiwen Ding, Siyue Wang, Wujie Wen, Youwei Zhuo, Chang Liu, Qinru Qiu, Wenyao Xu, Xue Lin, Xuehai Qian, Yanzhi Wang
It is a challenging task to have real-time, efficient, and accurate hardware RNN implementations because of the high sensitivity to imprecision accumulation and the requirement of special activation function implementations.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 13 Sep 2018 • Siyue Wang, Xiao Wang, Pu Zhao, Wujie Wen, David Kaeli, Peter Chin, Xue Lin
Based on the observations of the effect of test dropout rate on test accuracy and attack success rate, we propose a defensive dropout algorithm to determine an optimal test dropout rate given the neural network model and the attacker's strategy for generating adversarial examples. We also investigate the mechanism behind the outstanding defense effects achieved by the proposed defensive dropout.
no code implementations • 14 Mar 2018 • Yanzhi Wang, Zheng Zhan, Jiayu Li, Jian Tang, Bo Yuan, Liang Zhao, Wujie Wen, Siyue Wang, Xue Lin
Based on the universal approximation property, we further prove that SCNNs and BNNs exhibit the same energy complexity.