A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation

no code implementations • 19 May 2023 • Xiaowei Huang, Wenjie Ruan, Wei Huang, Gaojie Jin, Yi Dong, Changshun Wu, Saddek Bensalem, Ronghui Mu, Yi Qi, Xingyu Zhao, Kaiwen Cai, Yanghao Zhang, Sihao Wu, Peipei Xu, Dengyu Wu, Andre Freitas, Mustafa A. Mustafa

Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains.

Randomized Adversarial Training via Taylor Expansion

1 code implementation • CVPR 2023 • Gaojie Jin, Xinping Yi, Dengyu Wu, Ronghui Mu, Xiaowei Huang

The randomized weights enable our design of a novel adversarial training method via Taylor expansion of a small Gaussian noise, and we show that the new adversarial training method can flatten loss landscape and find flat minima.

Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff

1 code implementation • 23 Jan 2023 • Dengyu Wu, Gaojie Jin, Han Yu, Xinping Yi, Xiaowei Huang

The Top-K cutoff technique optimises the inference of SNN, and the regularisation are proposed to affect the training and construct SNN with optimised performance for cutoff.

Computational Efficiency

A Little Energy Goes a Long Way: Build an Energy-Efficient, Accurate Spiking Neural Network from Convolutional Neural Network

1 code implementation • 1 Mar 2021 • Dengyu Wu, Xinping Yi, Xiaowei Huang

In this paper, we argue that this trend of "energy for accuracy" is not necessary -- a little energy can go a long way to achieve the near-zero accuracy loss.