Related papers: Poisoning Bayesian Inference via Data Deletion and…
Collecting training data from untrusted sources exposes machine learning services to poisoning adversaries, who maliciously manipulate training data to degrade the model accuracy. When trained on offline datasets, poisoning adversaries have…
Machine learning models are currently being deployed in a variety of real-world applications where model predictions are used to make decisions about healthcare, bank loans, and numerous other critical tasks. As the deployment of artificial…
Decision-based attacks construct adversarial examples against a machine learning (ML) model by making only hard-label queries. These attacks have mainly been applied directly to standalone neural networks. However, in practice, ML models…
Machine learning has been widely applied in wireless communications. However, the security aspects of machine learning in wireless applications have not been well understood yet. We consider the case that a cognitive transmitter senses the…
Modern applications of artificial neural networks have yielded remarkable performance gains in a wide range of tasks. However, recent studies have discovered that such modelling strategy is vulnerable to Adversarial Examples, i.e. examples…
The lifecycle of large language models (LLMs) is far more complex than that of traditional machine learning models, involving multiple training stages, diverse data sources, and varied inference methods. While prior research on data…
Attacks on machine learning models have been, since their conception, a very persistent and evasive issue resembling an endless cat-and-mouse game. One major variant of such attacks is poisoning attacks which can indirectly manipulate an ML…
Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on…
Data Poisoning attacks modify training data to maliciously control a model trained on such data. In this work, we focus on targeted poisoning attacks which cause a reclassification of an unmodified test image and as such breach model…
Making learners robust to adversarial perturbation at test time (i.e., evasion attacks) or training time (i.e., poisoning attacks) has emerged as a challenging task. It is known that for some natural settings, sublinear perturbations in the…
These days, deep learning models have achieved great success in multiple fields, from autonomous driving to medical diagnosis. These models have expanded the abilities of artificial intelligence by offering great solutions to complex…
We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning. In addition to complying with data deletion requests, one often-cited potential application for unlearning…
Adversarial training (AT) is a robust learning algorithm that can defend against adversarial attacks in the inference phase and mitigate the side effects of corrupted data in the training phase. As such, it has become an indispensable…
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…
Model distillation has become essential for creating smaller, deployable language models that retain larger system capabilities. However, widespread deployment raises concerns about resilience to adversarial manipulation. This paper…
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,…
Model poisoning attacks are critical security threats to Federated Learning (FL). Existing model poisoning attacks suffer from two key limitations: 1) they achieve suboptimal effectiveness when defenses are deployed, and/or 2) they require…
Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously unrecognized threat to robust machine learning…
As machine learning (ML) becomes more and more powerful and easily accessible, attackers increasingly leverage ML to perform automated large-scale inference attacks in various domains. In such an ML-equipped inference attack, an attacker…
Data poisoning is a threat model in which a malicious actor tampers with training data to manipulate outcomes at inference time. A variety of defenses against this threat model have been proposed, but each suffers from at least one of the…