Related papers: Label-only Model Inversion Attack: The Attack that…
Removing information from a machine learning model is a non-trivial task that requires to partially revert the training process. This task is unavoidable when sensitive data, such as credit card numbers or passwords, accidentally enter the…
The purpose of anonymizing structured data is to protect the privacy of individuals in the data while retaining the statistical properties of the data. An important class of attack on anonymized data is attribute inference, where an…
Text classification has become widely used in various natural language processing applications like sentiment analysis. Current applications often use large transformer-based language models to classify input texts. However, there is a lack…
This study investigates the privacy risks associated with text embeddings, focusing on the scenario where attackers cannot access the original embedding model. Contrary to previous research requiring direct model access, we explore a more…
Few-shot learning arises in important practical scenarios, such as when a natural language understanding system needs to learn new semantic labels for an emerging, resource-scarce domain. In this paper, we explore retrieval-based methods…
Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the…
Gradient inversion (GI) attacks present a threat to the privacy of clients in federated learning (FL) by aiming to enable reconstruction of the clients' data from communicated model updates. A number of such techniques attempts to…
Recently, reconstruction-based anomaly detection was proposed as an effective technique to detect attacks in dynamic industrial control networks. Unlike classical network anomaly detectors that observe the network traffic,…
Machine Unlearning (MU) aims to update Machine Learning (ML) models following requests to remove training samples and their influences on a trained model efficiently without retraining the original ML model from scratch. While MU itself has…
Two-party split learning is a popular technique for learning a model across feature-partitioned data. In this work, we explore whether it is possible for one party to steal the private label information from the other party during split…
We design blackbox transfer-based targeted adversarial attacks for an environment where the attacker's source model and the target blackbox model may have disjoint label spaces and training datasets. This scenario significantly differs from…
Machine learning models can leak information regarding the dataset they have trained. In this paper, we present the first membership inference attack against black-boxed object detection models that determines whether the given data records…
Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and…
We consider the hard label based black box adversarial attack setting which solely observes predicted classes from the target model. Most of the attack methods in this setting suffer from impractical number of queries required to achieve a…
Previous studies have verified that the functionality of black-box models can be stolen with full probability outputs. However, under the more practical hard-label setting, we observe that existing methods suffer from catastrophic…
Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…
Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This…
Model Inversion Attacks (MIAs) pose a significant threat to data privacy by reconstructing sensitive training samples from the knowledge embedded in trained machine learning models. Despite recent progress in enhancing the effectiveness of…
Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs), enabling them to operate normally on clean inputs but manipulate predictions when specific trigger patterns occur. Currently, post-training backdoor…
Influence estimation tools -- such as memorization scores -- are widely used to understand model behavior, attribute training data, and inform dataset curation. However, recent applications in data valuation and responsible machine learning…