相关论文: Defending Regression Learners Against Poisoning At…

Recently, NLP has seen a surge in the usage of large pre-trained models. Users download weights of models pre-trained on large datasets, then fine-tune the weights on a task of their choice. This raises the question of whether downloading…

Data poisoning and leakage risks impede the massive deployment of federated learning in the real world. This chapter reveals the truths and pitfalls of understanding two dominating threats: {\em training data privacy intrusion} and {\em…

Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. Provably bounding model behavior under such attacks remains…

Adversarial attacks on deep-learning models pose a serious threat to their reliability and security. Existing defense mechanisms are narrow addressing a specific type of attack or being vulnerable to sophisticated attacks. We propose a new…

In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adversarial backdoor…

Machine learning based data-driven technologies have shown impressive performances in a variety of application domains. Most enterprises use data from multiple sources to provide quality applications. The reliability of the external data…

Graph Neural Networks (GNNs) have achieved promising results in tasks such as node classification and graph classification. However, recent studies reveal that GNNs are vulnerable to backdoor attacks, posing a significant threat to their…

Research in adversarial machine learning (AML) has shown that statistical models are vulnerable to maliciously altered data. However, despite advances in Bayesian machine learning models, most AML research remains concentrated on classical…

The performance of machine learning models depends on the quality of the underlying data. Malicious actors can attack the model by poisoning the training data. Current detectors are tied to either specific data types, models, or attacks,…

Learning in adversarial settings is becoming an important task for application domains where attackers may inject malicious data into the training set to subvert normal operation of data-driven technologies. Feature selection has been…

The notion of local intrinsic dimensionality (LID) is an important advancement in data dimensionality analysis, with applications in data mining, machine learning and similarity search problems. Existing distance-based LID estimators were…

We consider data poisoning attacks, a class of adversarial attacks on machine learning where an adversary has the power to alter a small fraction of the training data in order to make the trained classifier satisfy certain objectives. While…

In this paper, we study PAC learnability and certification of predictions under instance-targeted poisoning attacks, where the adversary who knows the test instance may change a fraction of the training set with the goal of fooling the…

Two widely used techniques for training supervised machine learning models on small datasets are Active Learning and Transfer Learning. The former helps to optimally use a limited budget to label new data. The latter uses large pre-trained…

Despite their remarkable performance, deep neural networks exhibit a critical vulnerability: small, often imperceptible, adversarial perturbations can lead to drastically altered model predictions. Given the stringent reliability demands of…

Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…

Learning reward models from pairwise comparisons is a fundamental component in a number of domains, including autonomous control, conversational agents, and recommendation systems, as part of a broad goal of aligning automated decisions…

Deep networks are well-known to be fragile to adversarial attacks. We conduct an empirical analysis of deep representations under the state-of-the-art attack method called PGD, and find that the attack causes the internal representation to…

Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…