Search Results for author:
Found 40 papers, 18 papers with code
Leveraging Local Structure for Improving Model Explanations: An Information Propagation Approach
For image classifiers, these methods typically provide an attribution score to each pixel in the image to quantify its contribution to the prediction.
Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspective
Federated learning (FL) is an emerging collaborative learning paradigm that aims to protect data privacy.
Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence
DP-SGD) to significantly boost accuracy and convergence.
Graph Neural Network Causal Explanation via Neural Causal Models
Our explainer is based on the observation that a graph often consists of a causal underlying subgraph.
Graph Neural Network Explanations are Fragile
Explainable Graph Neural Network (GNN) has emerged recently to foster the trust of using GNNs.
Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics
Graph Neural Networks (GNNs) have gained popularity in numerous domains, yet they are vulnerable to backdoor attacks that can compromise their performance and ethical application.
Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks
Machine learning (ML) is vulnerable to inference (e. g., membership inference, property inference, and data reconstruction) attacks that aim to infer the private information of training data or dataset.
PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
Based on this attack surface, we propose PoisonedRAG, the first knowledge corruption attack to RAG, where an attacker could inject a few malicious texts into the knowledge database of a RAG system to induce an LLM to generate an attacker-chosen target answer for an attacker-chosen target question.
M-Net: A Lightweight Network Based on Multilayer Perceptron for Massive MIMO CSI Feedback
Finally, we demonstrate that the M-Net variants achieve the SOTA performance by only deep enning the M-Net decoder.
Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks
The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks.
Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
Specifically, we establish a novel theoretical foundation for ensuring the ASP of the black-box attack with randomized adversarial examples (AEs).
A Certified Radius-Guided Attack Framework to Image Segmentation Models
We are the first, from the attacker perspective, to leverage the properties of certified radius and propose a certified radius guided attack framework against image segmentation models.
IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients
Integrated Gradients (IG) as well as its variants are well-known techniques for interpreting the decisions of deep neural networks.
UniCR: Universally Approximated Certified Robustness via Randomized Smoothing
We study certified robustness of machine learning classifiers against adversarial perturbations.
NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks
Membership inference attacks (MIAs) against machine learning models can lead to serious privacy risks for the training dataset used in the model training.
Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guarantees
We then propose an online attack based on bandit optimization which is proven to be {sublinear} to the query number $T$, i. e., $\mathcal{O}(\sqrt{N}T^{3/4})$ where $N$ is the number of nodes in the graph.
Detecting Gender Bias in Transformer-based Models: A Case Study on BERT
In this paper, we propose a novel gender bias detection method by utilizing attention map for transformer-based models.
Bandits for Black-box Attacks to Graph Neural Networks with Structure Perturbation
However, many recent works have demonstrated that an attacker can mislead GNN models by slightly perturbing the graph structure.
A Hard Label Black-box Adversarial Attack Against Graph Neural Networks
We also evaluate the effectiveness of our attack under two defenses: one is well-designed adversarial graph detector and the other is that the target GNN model itself is equipped with a defense to prevent adversarial graph generation.
Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective
Existing representation learning methods on graphs have achieved state-of-the-art performance on various graph-related tasks such as node classification, link prediction, etc.
Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective
The key idea of our defense is learning to perturb data representation such that the quality of the reconstructed data is severely degraded, while FL performance is maintained.
Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting
Crowd counting has drawn much attention due to its importance in safety-critical surveillance systems.
Semi-Supervised Node Classification on Graphs: Markov Random Fields vs. Graph Neural Networks
In this work, we aim to address the key limitation of existing pMRF-based methods.
Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective
In this work, we show our key observation that the data representation leakage from gradients is the essential cause of privacy leakage in FL.
GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs
However, existing FL methods 1) perform poorly when data across clients are non-IID, 2) cannot handle data with new label domains, and 3) cannot leverage unlabeled data, while all these issues naturally happen in real-world graph-based problems.
Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations
For instance, our method can build a classifier that achieves a certified top-3 accuracy of 69. 2\% on ImageNet when an attacker can arbitrarily perturb 5 pixels of a testing image.
Robust and Verifiable Information Embedding Attacks to Deep Neural Networks via Error-Correcting Codes
Moreover, to be robust against post-processing, we leverage Turbo codes, a type of error-correcting codes, to encode the message before embedding it to the DNN classifier.
Reinforcement Learning-based Black-Box Evasion Attacks to Link Prediction in Dynamic Graphs
Link prediction in dynamic graphs (LPDG) is an important research problem that has diverse applications such as online recommendations, studies on disease contagion, organizational studies, etc.
Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function
Specifically, we first introduce two influence functions, i. e., feature-label influence and label influence, that are defined on GNNs and label propagation (LP), respectively.
Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation
Specifically, we prove the certified robustness guarantee of any GNN for both node and graph classifications against structural perturbation.
Cryptography and Security
LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets
Rather than learning a shared global model in classic federated learning, each client learns a personalized model via LotteryFL; the communication cost can be significantly reduced due to the compact size of lottery networks.
Backdoor Attacks to Graph Neural Networks
Specifically, we propose a \emph{subgraph based backdoor attack} to GNN for graph classification.
Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability
We consider the blackbox transfer-based targeted adversarial attack threat model in the realm of deep neural network (DNN) image classifiers.
On Certifying Robustness against Backdoor Attacks via Randomized Smoothing
Specifically, in this work, we study the feasibility and effectiveness of certifying robustness against backdoor attacks using a recent technique called randomized smoothing.
Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing
However, several recent studies showed that community detection is vulnerable to adversarial structural perturbation.
Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing
For example, our method can obtain an ImageNet classifier with a certified top-5 accuracy of 62. 8\% when the $\ell_2$-norms of the adversarial perturbations are less than 0. 5 (=127/255).
Attacking Graph-based Classification via Manipulating the Graph Structure
Results show that our attacks 1) can effectively evade graph-based classification methods; 2) do not require access to the true parameters, true training dataset, and/or complete graph; and 3) outperform the existing attack for evading collective classification methods and some graph neural network methods.
Cryptography and Security
Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation
To address the computational challenge, we propose to jointly learn the edge weights and propagate the reputation scores, which is essentially an approximate solution to the optimization problem.
Stealing Hyperparameters in Machine Learning
In this work, we propose attacks on stealing the hyperparameters that are learned by a learner.
Robust Multi-subspace Analysis Using Novel Column L0-norm Constrained Matrix Factorization
To tackle all these problems, we propose a method, called Matrix Factorization with Column L0-norm constraint (MFC0), that can simultaneously learn the basis for each subspace, generate a direct sparse representation for each data sample, as well as removing errors in the data in an efficient way.
