1 code implementation • 28 Feb 2024 • Siqi Kou, Lanxiang Hu, Zhezhi He, Zhijie Deng, Hao Zhang
Parallel decoding methods such as Jacobi decoding show promise for more efficient LLM inference as it breaks the sequential nature of the LLM decoding process and transforms it into parallelizable computation.
1 code implementation • CVPR 2019 • Adnan Siraj Rakin, Zhezhi He, Deliang Fan
Training the network with Gaussian noise is an effective technique to perform model regularization, thus improving model robustness against input variation.
1 code implementation • ICCV 2019 • Adnan Siraj Rakin, Zhezhi He, Deliang Fan
Several important security issues of Deep Neural Network (DNN) have been raised recently associated with different applications and components.
1 code implementation • CVPR 2020 • Zhezhi He, Adnan Siraj Rakin, Jingtao Li, Chaitali Chakrabarti, Deliang Fan
Recently, a new paradigm of the adversarial attack on the quantized neural network weights has attracted great attention, namely, the Bit-Flip based adversarial weight attack, aka.
1 code implementation • CVPR 2022 • Jingtao Li, Adnan Siraj Rakin, Xing Chen, Zhezhi He, Deliang Fan, Chaitali Chakrabarti
While such a scheme helps reduce the computational load at the client end, it opens itself to reconstruction of raw data from intermediate activation by the server.
3 code implementations • CVPR 2020 • Adnan Siraj Rakin, Zhezhi He, Deliang Fan
However, when the attacker activates the trigger by embedding it with any input, the network is forced to classify all inputs to a certain target class.
1 code implementation • 15 Dec 2021 • Yu Gong, Zhihan Xu, Zhezhi He, Weifeng Zhang, Xiaobing Tu, Xiaoyao Liang, Li Jiang
From the software perspective, we mathematically and systematically model the latency and resource utilization of the proposed heterogeneous accelerator, regarding varying system design configurations.
1 code implementation • 9 Mar 2022 • Zhuoran Song, Yihong Xu, Zhezhi He, Li Jiang, Naifeng Jing, Xiaoyao Liang
We explore the sparsity in ViT and observe that informative patches and heads are sufficient for accurate image recognition.
1 code implementation • ICCV 2021 • Fangxin Liu, Wenbo Zhao, Zhezhi He, Yanzhi Wang, Zongwu Wang, Changzhi Dai, Xiaoyao Liang, Li Jiang
Model quantization has emerged as a mandatory technique for efficient inference with advanced Deep Neural Networks (DNN).
2 code implementations • 24 Jul 2020 • Adnan Siraj Rakin, Zhezhi He, Jingtao Li, Fan Yao, Chaitali Chakrabarti, Deliang Fan
Prior works of BFA focus on un-targeted attack that can hack all inputs into a random output class by flipping a very small number of weight bits stored in computer memory.
1 code implementation • 20 Jan 2021 • Jingtao Li, Adnan Siraj Rakin, Zhezhi He, Deliang Fan, Chaitali Chakrabarti
In this work, we propose RADAR, a Run-time adversarial weight Attack Detection and Accuracy Recovery scheme to protect DNN weights against PBFA.
no code implementations • 5 Feb 2018 • Adnan Siraj Rakin, Zhezhi He, Boqing Gong, Deliang Fan
Blind pre-processing improves the white box attack accuracy of MNIST from 94. 3\% to 98. 7\%.
no code implementations • 8 May 2017 • Zhezhi He, Deliang Fan
In this work, we have proposed a revolutionary neuromorphic computing methodology to implement All-Skyrmion Spiking Neural Network (AS-SNN).
no code implementations • 20 Jul 2018 • Zhezhi He, Boqing Gong, Deliang Fan
Deep convolution neural network has achieved great success in many artificial intelligence applications.
no code implementations • CVPR 2019 • Zhezhi He, Deliang Fan
In the past years, Deep convolution neural network has achieved great success in many artificial intelligence applications.
no code implementations • 30 May 2019 • Adnan Siraj Rakin, Zhezhi He, Li Yang, Yanzhi Wang, Liqiang Wang, Deliang Fan
In this work, we show that shrinking the model size through proper weight pruning can even be helpful to improve the DNN robustness under adversarial attack.
no code implementations • 3 Jul 2019 • Xiaolong Ma, Sheng Lin, Shaokai Ye, Zhezhi He, Linfeng Zhang, Geng Yuan, Sia Huat Tan, Zhengang Li, Deliang Fan, Xuehai Qian, Xue Lin, Kaisheng Ma, Yanzhi Wang
Based on the proposed comparison framework, with the same accuracy and quantization, the results show that non-structrued pruning is not competitive in terms of both storage and computation efficiency.
no code implementations • CVPR 2021 • Li Yang, Zhezhi He, Junshan Zhang, Deliang Fan
Thus motivated, we propose a new training method called \textit{kernel-wise Soft Mask} (KSM), which learns a kernel-wise hybrid binary and real-value soft mask for each task, while using the same backbone model.
no code implementations • 11 Sep 2020 • Li Yang, Zhezhi He, Yu Cao, Deliang Fan
Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently.
no code implementations • 25 Nov 2020 • Sen Lin, Li Yang, Zhezhi He, Deliang Fan, Junshan Zhang
In this work, we advocate a holistic approach to jointly train the backbone network and the channel gating which enables dynamical selection of a subset of filters for more efficient local computation given the data input.
no code implementations • 2 Mar 2021 • Fangxin Liu, Wenbo Zhao, Yilong Zhao, Zongwu Wang, Tao Yang, Zhezhi He, Naifeng Jing, Xiaoyao Liang, Li Jiang
However, it is challenging for crossbar architecture to exploit the sparsity in the DNN.
no code implementations • 13 Mar 2023 • Jingtao Li, Adnan Siraj Rakin, Xing Chen, Li Yang, Zhezhi He, Deliang Fan, Chaitali Chakrabarti
We show that under practical cases, the proposed ME attacks work exceptionally well for SFL.