20 citations · 77 across the 19 of their papers we have counts for
19 papers
S2O: Enhancing Adversarial Training with Second-Order Statistics of Weights
Gaojie Jin, Xinping Yi, Wei Huang +2
Adversarial training has emerged as a highly effective way to improve the robustness of deep neural networks (DNNs). It is typically conceptualized as a min-max optimization proble…
Towards A Unified PAC-Bayesian Framework for Norm-based Generalization Bounds
Xinping Yi, Gaojie Jin, Xiaowei Huang +1
Understanding the generalization behavior of deep neural networks remains a fundamental challenge in modern statistical learning theory. Among existing approaches, PAC-Bayesian nor…
Reconcile Certified Robustness and Accuracy for DNN-based Smoothed Majority Vote Classifier
Gaojie Jin, Xinping Yi, Xiaowei Huang
Within the PAC-Bayesian framework, the Gibbs classifier (defined on a posterior ) and the corresponding -weighted majority vote classifier are commonly used to analyze the ge…
Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models
Sihao Wu, Gaojie Jin, Wei Huang +2
Vision Language Models (VLMs) have demonstrated impressive capabilities in integrating visual and textual information for understanding and reasoning, but remain highly vulnerable…
Shapley Uncertainty in Natural Language Generation
Meilin Zhu, Gaojie Jin, Xiaowei Huang +1
In question-answering tasks, determining when to trust the outputs is crucial to the alignment of large language models (LLMs). Kuhn et al. (2023) introduces semantic entropy as a…
ThermoRL:Structure-Aware Reinforcement Learning for Protein Mutation Design to Enhance Thermostability
Xiangwen Wang, Gaojie Jin, Xiaowei Huang +1
Designing mutations to optimize protein thermostability remains challenging due to the complex relationship between sequence variations, structural dynamics, and thermostability, o…
Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environments
Gaojie Jin, Ronghui Mu, Xinping Yi +2
The Invariant Risk Minimization (IRM) approach aims to address the challenge of domain generalization by training a feature representation that remains invariant across multiple en…
Safeguarding Large Language Models: A Survey
Yi Dong, Ronghui Mu, Yanghao Zhang +9
In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as "safeguards" or "guardrails", has become imperative to ensure t…
Direct Training Needs Regularisation: Anytime Optimal Inference Spiking Neural Network
Dengyu Wu, Yi Qi, Kaiwen Cai +3
Spiking Neural Network (SNN) is acknowledged as the next generation of Artificial Neural Network (ANN) and hold great promise in effectively processing spatial-temporal information…
Building Guardrails for Large Language Models
Yi Dong, Ronghui Mu, Gaojie Jin +6
As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts…
TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models
Liang Zhang, Nathaniel Xu, Pengfei Yang +3
Robust pedestrian trajectory forecasting is crucial to developing safe autonomous vehicles. Although previous works have studied adversarial robustness in the context of trajectory…
A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation
Xiaowei Huang, Wenjie Ruan, Wei Huang +14
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…
Randomized Adversarial Training via Taylor Expansion
Gaojie Jin, Xinping Yi, Dengyu Wu +2
In recent years, there has been an explosion of research into developing more robust deep neural networks against adversarial examples. Adversarial training appears as one of the m…
Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff
Dengyu Wu, Gaojie Jin, Han Yu +2
Spiking neural network (SNN), as the next generation of artificial neural network (ANN), offer a closer mimicry of natural neural networks and hold promise for significant improvem…
SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability
Wei Huang, Xingyu Zhao, Gaojie Jin +1
Interpretability of Deep Learning (DL) is a barrier to trustworthy AI. Despite great efforts made by the Explainable AI (XAI) community, explanations lack robustness -- indistingui…
Enhancing Adversarial Training with Second-Order Statistics of Weights
Gaojie Jin, Xinping Yi, Wei Huang +2
Adversarial training has been shown to be one of the most effective approaches to improve the robustness of deep neural networks. It is formalized as a min-max optimization over mo…
Neuronal Correlation: a Central Concept in Neural Network
Gaojie Jin, Xinping Yi, Xiaowei Huang
This paper proposes to study neural networks through neuronal correlation, a statistical measure of correlated neuronal activity on the penultimate layer. We show that neuronal cor…
Weight Expansion: A New Perspective on Dropout and Generalization
Gaojie Jin, Xinping Yi, Pengfei Yang +3
While dropout is known to be a successful regularization technique, insights into the mechanisms that lead to this success are still lacking. We introduce the concept of \emph{weig…
How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networks
Gaojie Jin, Xinping Yi, Liang Zhang +3
This paper studies the novel concept of weight correlation in deep neural networks and discusses its impact on the networks' generalisation ability. For fully-connected layers, the…