Search Results for author:
Found 79 papers, 36 papers with code
Normative Multiagent Systems: A Dynamic Generalization
Social norms are powerful formalism in coordinating autonomous agents' behaviour to achieve certain objectives.
Safety Verification of Deep Neural Networks
Our method works directly with the network code and, in contrast to existing methods, can guarantee that adversarial examples, if they exist, are found for the given region and family of manipulations.
Feature-Guided Black-Box Safety Testing of Deep Neural Networks
In this paper, we focus on image classifiers and propose a feature-guided black-box approach to test the safety of deep neural networks that requires no such knowledge.
Testing Deep Neural Networks
In this paper, inspired by the MC/DC coverage criterion, we propose a family of four novel test criteria that are tailored to structural features of DNNs and their semantics.
Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the $L_0$ Norm
In this paper we focus on the $L_0$ norm and aim to compute, for a trained DNN and an input, the maximal radius of a safe norm ball around the input within which there are no adversarial examples.
Concolic Testing for Deep Neural Networks
Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program.
Reachability Analysis of Deep Neural Networks with Provable Guarantees
Verifying correctness of deep neural networks (DNNs) is challenging.
A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees
In this paper, we study two variants of pointwise robustness, the maximum safe radius problem, which for a given input sample computes the minimum distance to an adversarial example, and the feature robustness problem, which aims to quantify the robustness of individual features to adversarial perturbations.
A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
In the past few years, significant progress has been made on deep neural networks (DNNs) in achieving human-level performance on several long-standing tasks.
Analyzing Deep Neural Networks with Symbolic Propagation: Towards Higher Precision and Faster Verification
Several verification approaches have been developed to automatically prove or disprove safety properties of DNNs.
testRNN: Coverage-guided Testing on Recurrent Neural Networks
Recurrent neural networks (RNNs) have been widely applied to various sequential tasks such as text processing, video recognition, and molecular property prediction.
HITSZ-ICRC: A Report for SMM4H Shared Task 2019-Automatic Classification and Extraction of Adverse Effect Mentions in Tweets
This is the system description of the Harbin Institute of Technology Shenzhen (HITSZ) team for the first and second subtasks of the fourth Social Media Mining for Health Applications (SMM4H) shared task in 2019.
Explaining Image Classifiers using Statistical Fault Localization
The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for "Explainable AI".
Towards Integrating Formal Verification of Autonomous Robots with Battery Prognostics and Health Management
The battery is a key component of autonomous robots.
Coverage Guided Testing for Recurrent Neural Networks
The test metrics and test case generation algorithm are implemented into a tool TestRNN, which is then evaluated on a set of LSTM benchmarks.
Reliability Validation of Learning Enabled Vehicle Tracking
However, it is unclear if and how the adversarial examples over learning components can affect the overall system-level reliability.
A Safety Framework for Critical Systems Utilising Deep Neural Networks
Increasingly sophisticated mathematical modelling processes from Machine Learning are being used to analyse complex data.
Generating Adversarial Inputs Using A Black-box Differential Technique
Algorithmically, DAEGEN uses a local search-based optimization algorithm to find DIAEs by iteratively perturbing an input to maximize the difference of two models on predicting the input.
Adaptable and Verifiable BDI Reasoning
Long-term autonomy requires autonomous systems to adapt as their capabilities no longer perform as expected.
CasGCN: Predicting future cascade growth based on information diffusion graph
In this paper, we propose a novel deep learning architecture for cascade growth prediction, called CasGCN, which employs the graph convolutional network to extract structural features from a graphical input, followed by the application of the attention mechanism on both the extracted features and the temporal information before conducting cascade size prediction.
Towards the Quantification of Safety Risks in Deep Neural Networks
In this paper, we define safety risks by requesting the alignment of the network's decision with human perception.
How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networks
This paper studies the novel concept of weight correlation in deep neural networks and discusses its impact on the networks' generalisation ability.
Generalizing Universal Adversarial Attacks Beyond Additive Perturbations
Extensive experiments are conducted on CIFAR-10 and ImageNet datasets with six deep neural network models including GoogleLeNet, VGG16/19, ResNet101/152, and DenseNet121.
Embedding and Extraction of Knowledge in Tree Ensemble Classifiers
Whilst, as the increasing use of machine learning models in security-critical applications, the embedding and extraction of malicious knowledge are equivalent to the notorious backdoor attack and its defence, respectively.
How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?
This paper studies the novel concept of weight correlation in deep neural networks and discusses its impact on the networks' generalisation ability.
BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations
Given the pressing need for assuring algorithmic transparency, Explainable AI (XAI) has emerged as one of the key areas of AI research.
A Little Energy Goes a Long Way: Build an Energy-Efficient, Accurate Spiking Neural Network from Convolutional Neural Network
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.
Abstraction and Symbolic Execution of Deep Neural Networks with Bayesian Approximation of Hidden Features
Intensive research has been conducted on the verification and validation of deep neural networks (DNNs), aiming to understand if, and how, DNNs can be applied to safety critical applications.
Detecting Operational Adversarial Examples for Reliable Deep Learning
The utilisation of Deep Learning (DL) raises new challenges regarding its dependability in critical applications.
Learning Robust Variational Information Bottleneck with Reference
We propose a new approach to train a variational information bottleneck (VIB) that improves its robustness to adversarial perturbations.
Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles
The utilisation of Deep Learning (DL) is advancing into increasingly more sophisticated applications.
Spatial Uncertainty-Aware Semi-Supervised Crowd Counting
Semi-supervised approaches for crowd counting attract attention, as the fully supervised paradigm is expensive and laborious due to its request for a large number of images of dense crowd scenarios and their annotations.
Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications
This tutorial aims to introduce the fundamentals of adversarial robustness of deep learning, presenting a well-structured review of up-to-date techniques to assess the vulnerability of various types of deep learning models to adversarial examples.
Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking
While Deep Reinforcement Learning (DRL) provides transformational capabilities to the control of Robotics and Autonomous Systems (RAS), the black-box nature of DRL and uncertain deployment environments of RAS pose new challenges on its dependability.
BI-GCN: Boundary-Aware Input-Dependent Graph Convolution Network for Biomedical Image Segmentation
Our model is well-suited to obtain global semantic region information while also accommodates local spatial boundary characteristics simultaneously.
Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance
The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) -- has resulted in the pressing need to assure their functional safety.
GPS: A Policy-driven Sampling Approach for Graph Representation Learning
Graph representation learning has drawn increasing attention in recent years, especially for learning the low dimensional embedding at both node and graph level for classification and recommendations tasks.
Neuronal Correlation: a Central Concept in Neural Network
This paper proposes to study neural networks through neuronal correlation, a statistical measure of correlated neuronal activity on the penultimate layer.
Weight Expansion: A New Perspective on Dropout and Generalization
While dropout is known to be a successful regularization technique, insights into the mechanisms that lead to this success are still lacking.
STUN: Self-Teaching Uncertainty Estimation for Place Recognition
Then, supervised by the pretrained teacher net, a student net with an additional variance branch is trained to finetune the embedding priors and estimate the uncertainty sample by sample.
Counting with Adaptive Auxiliary Learning
This paper proposes an adaptive auxiliary task learning based approach for object counting problems.
3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs
In this paper, we propose a novel multi-level aggregation network to regress the coordinates of the vertices of a 3D face from a single 2D image in an end-to-end manner.
Enhancing Adversarial Training with Second-Order Statistics of Weights
In this paper, we show that treating model weights as random variables allows for enhancing adversarial training through \textbf{S}econd-Order \textbf{S}tatistics \textbf{O}ptimization (S$^2$O) with respect to the weights.
Hierarchical Distribution-Aware Testing of Deep Learning
In this paper, we propose a new robustness testing approach for detecting AEs that considers both the feature level distribution and the pixel level distribution, capturing the perceptual quality of adversarial perturbations.
An Adaptive Federated Relevance Framework for Spatial Temporal Graph Learning
Spatial-temporal data contains rich information and has been widely studied in recent years due to the rapid development of relevant applications in many fields.
Short-term Load Forecasting with Distributed Long Short-Term Memory
With the employment of smart meters, massive data on consumer behaviour can be collected by retailers.
SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability
Finally, we demonstrate two applications of our methods: ranking robust XAI methods and selecting training schemes to improve both classification and interpretation robustness.
Uncertainty Estimation for 3D Dense Prediction via Cross-Point Embeddings
In this work, we present CUE, a novel uncertainty estimation method for dense prediction tasks in 3D point clouds.
Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems
Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RAS).
Towards Relation-centered Pooling and Convolution for Heterogeneous Graph Learning Networks
Heterogeneous graph neural network has unleashed great potential on graph representation learning and shown superior performance on downstream tasks such as node classification and clustering.
Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff
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.
Towards Verifying the Geometric Robustness of Large-scale Neural Networks
Deep neural networks (DNNs) are known to be vulnerable to adversarial geometric transformation.
Decentralised and Cooperative Control of Multi-Robot Systems through Distributed Optimisation
Then, based on the distributed optimisation algorithm, an output regulation method is utilised to solve the optimal coordination problem for general linear dynamic systems.
Randomized Adversarial Training via Taylor Expansion
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.
Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT
Can safety analysis make use of Large Language Models (LLMs)?
Model-Agnostic Reachability Analysis on Deep Neural Networks
Verification plays an essential role in the formal analysis of safety-critical systems.
A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation
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.
DSHGT: Dual-Supervisors Heterogeneous Graph Transformer -- A pioneer study of using heterogeneous graph learning for detecting software vulnerabilities
Vulnerability detection is a critical problem in software security and attracts growing attention both from academia and industry.
Learning by Analogy: Diverse Questions Generation in Math Word Problem
We then feed them to a question generator together with the scenario to obtain the corresponding diverse questions, forming a new MWP with a variety of questions and equations.
Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs
Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility in modeling complex graph structure data.
Risk Controlled Image Retrieval
Most image retrieval research focuses on improving predictive performance, ignoring scenarios where the reliability of the prediction is also crucial.
What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems
Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges.
A Symbolic Character-Aware Model for Solving Geometry Problems
For the diagram encoder, we pre-train it under a multi-label classification framework with the symbolic characters as labels.
MathAttack: Attacking Large Language Models Towards Math Solving Ability
Instead of attacking prompts in the use of LLMs, we propose a MathAttack model to attack MWP samples which are closer to the essence of security in solving math problems.
Exploiting Spatial-temporal Data for Sleep Stage Classification via Hypergraph Learning
Sleep stage classification is crucial for detecting patients' health conditions.
Symplectic Structure-Aware Hamiltonian (Graph) Embeddings
In traditional Graph Neural Networks (GNNs), the assumption of a fixed embedding manifold often limits their adaptability to diverse graph geometries.
DeepHGCN: Toward Deeper Hyperbolic Graph Convolutional Networks
Hyperbolic graph convolutional networks (HGCN) have demonstrated significant potential in extracting information from hierarchical graphs.
GPT-Prompt Controlled Diffusion for Weakly-Supervised Semantic Segmentation
In this process, the existing images and image-level labels provide the necessary control information, where GPT is employed to enrich the prompts, leading to the generation of diverse backgrounds.
Top-K Pooling with Patch Contrastive Learning for Weakly-Supervised Semantic Segmentation
In this paper, we introduce a novel ViT-based WSSS method named top-K pooling with patch contrastive learning (TKP-PCL), which employs a top-K pooling layer to alleviate the limitations of previous max pooling selection.
Contrastive Learning
Weakly supervised Semantic Segmentation
+1
Reward Certification for Policy Smoothed Reinforcement Learning
Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it can be weakened by adversarial attacks.
ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning
Then, to mitigate the vulnerability of existing GCRL algorithms, we introduce Adversarial Representation Tactics, which combines Semi-Contrastive Adversarial Augmentation with Sensitivity-Aware Regularizer to improve the adversarial robustness of the underlying RL agent against various types of perturbations.
Building Guardrails for Large Language Models
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 on human users and societies.
Privacy-Preserving Distributed Learning for Residential Short-Term Load Forecasting
In the realm of power systems, the increasing involvement of residential users in load forecasting applications has heightened concerns about data privacy.
ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation
Text-to-Image (T2I) Diffusion Models (DMs) have shown impressive abilities in generating high-quality images based on simple text descriptions.
Towards Fairness-Aware Adversarial Learning
As a generalization of conventional AT, we re-define the problem of adversarial training as a min-max-max framework, to ensure both robustness and fairness of the trained model.
DeepCDCL: An CDCL-based Neural Network Verification Framework
Neural networks in safety-critical applications face increasing safety and security concerns due to their susceptibility to little disturbance.
BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection
Nevertheless, integrating OoD detection into state-of-the-art (SOTA) object detection DNNs poses significant challenges, partly due to the complexity introduced by the SOTA OoD construction methods, which require the modification of DNN architecture and the introduction of complex loss functions.
ADVREPAIR:Provable Repair of Adversarial Attack
Existing neuron-level methods using limited data lack efficacy in fixing adversaries due to the inherent complexity of adversarial attack mechanisms, while adversarial training, leveraging a large number of adversarial samples to enhance robustness, lacks provability.
Regression of Instance Boundary by Aggregated CNN and GCN
In particular, thanks to the proposed aggregation GCN, our network benefits from direct feature learning of the instances’ boundary locations and the spatial information propagation across the image.
