Search Results for author:
Found 20 papers, 4 papers with code
Defending Jailbreak Prompts via In-Context Adversarial Game
Large Language Models (LLMs) demonstrate remarkable capabilities across diverse applications.
Manipulating Predictions over Discrete Inputs in Machine Teaching
Machine teaching often involves the creation of an optimal (typically minimal) dataset to help a model (referred to as the `student') achieve specific goals given by a teacher.
BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning
Our algorithm, BadRL, strategically chooses state observations with high attack values to inject triggers during training and testing, thereby reducing the chances of detection.
MS-UNet-v2: Adaptive Denoising Method and Training Strategy for Medical Image Segmentation with Small Training Data
The proposed multi-scale nested decoder structure allows the feature mapping between the decoder and encoder to be semantically closer, thus enabling the network to learn more detailed features.
Decoding the Secrets of Machine Learning in Malware Classification: A Deep Dive into Datasets, Feature Extraction, and Model Performance
As a consequence, our community still lacks an understanding of malware classification results: whether they are tied to the nature and distribution of the collected dataset, to what extent the number of families and samples in the training dataset influence performance, and how well static and dynamic features complement each other.
BadVFL: Backdoor Attacks in Vertical Federated Learning
In VFL, the participants share the same set of training instances but only host a different and non-overlapping subset of the whole feature space.
Towards Efficient and Domain-Agnostic Evasion Attack with High-dimensional Categorical Inputs
Our work targets at searching feasible adversarial perturbation to attack a classifier with high-dimensional categorical inputs in a domain-agnostic setting.
AdvCat: Domain-Agnostic Robustness Assessment for Cybersecurity-Critical Applications with Categorical Inputs
Machine Learning-as-a-Service systems (MLaaS) have been largely developed for cybersecurity-critical applications, such as detecting network intrusions and fake news campaigns.
Cerberus: Exploring Federated Prediction of Security Events
Modern defenses against cyberattacks increasingly rely on proactive approaches, e. g., to predict the adversary's next actions based on past events.
Finding MNEMON: Reviving Memories of Node Embeddings
Previous security research efforts orbiting around graphs have been exclusively focusing on either (de-)anonymizing the graphs or understanding the security and privacy issues of graph neural networks.
Model Stealing Attacks Against Inductive Graph Neural Networks
Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications.
Learning to dehaze with polarization
Haze, a common kind of bad weather caused by atmospheric scattering, decreases the visibility of scenes and degenerates the performance of computer vision algorithms.
Towards Understanding the Robustness Against Evasion Attack on Categorical Data
Characterizing and assessing the adversarial vulnerability of classification models with categorical input has been a practically important, while rarely explored research problem.
Attack Transferability Characterization for Adversarially Robust Multi-label Classification
We unveil how the transferability level of the attack determines the attackability of the classifier via establishing an information-theoretic analysis of the adversarial risk.
Characterizing the Evasion Attackability of Multi-label Classifiers
Evasion attack in multi-label learning systems is an interesting, widely witnessed, yet rarely explored research topic.
Robust Multi-Output Learning with Highly Incomplete Data via Restricted Boltzmann Machines
In order to take full advantage of these dependencies we consider a purely probabilistic setting in which the features imputation and multi-label classification problems are jointly solved.
Prototypical Networks for Multi-Label Learning
We propose to formulate multi-label learning as a estimation of class distribution in a non-linear embedding space, where for each label, its positive data embeddings and negative data embeddings distribute compactly to form a positive component and negative component respectively, while the positive component and negative component are pushed away from each other.
Robust Federated Training via Collaborative Machine Teaching using Trusted Instances
In our work, we propose a collaborative and privacy-preserving machine teaching paradigm with multiple distributed teachers, to improve robustness of the federated training process against local data corruption.
Collaborative and Privacy-Preserving Machine Teaching via Consensus Optimization
To address these challenges, we formulate collaborative teaching as a consensus and privacy-preserving optimization process to minimize teaching risk.
Mini-Batch Spectral Clustering
The cost of computing the spectrum of Laplacian matrices hinders the application of spectral clustering to large data sets.
