Related papers: Influence Based Defense Against Data Poisoning Att…
We consider availability data poisoning attacks, where an adversary aims to degrade the overall test accuracy of a machine learning model by crafting small perturbations to its training data. Existing poisoning strategies can achieve the…
Data poisoning considers cases when an adversary manipulates the behavior of machine learning algorithms through malicious training data. Existing threat models of data poisoning center around a single metric, the number of poisoned…
Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server. However, the…
Recommender systems have become an integral part of online services to help users locate specific information in a sea of data. However, existing studies show that some recommender systems are vulnerable to poisoning attacks, particularly…
Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks…
We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…
State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…
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…
We show that by controlling parts of a physical environment in which a pre-trained deep neural network (DNN) is being fine-tuned online, an adversary can launch subtle data poisoning attacks that degrade the performance of the system. While…
The rise of foundation models fine-tuned on human feedback from potentially untrusted users has increased the risk of adversarial data poisoning, necessitating the study of robustness of learning algorithms against such attacks. Existing…
Machine learning models have achieved great success in supervised learning tasks for end-to-end training, which requires a large amount of labeled data that is not always feasible. Recently, many practitioners have shifted to…
Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process. Prior works focus on either availability attacks (i.e.,…
Machine learning systems are deployed in critical settings, but they might fail in unexpected ways, impacting the accuracy of their predictions. Poisoning attacks against machine learning induce adversarial modification of data used by a…
A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set. The watermark does not impact the test-time performance of the model on typical…
Property inference attacks consider an adversary who has access to the trained model and tries to extract some global statistics of the training data. In this work, we study property inference in scenarios where the adversary can…
Emerging technologies drive the ongoing transformation of Intelligent Transportation Systems (ITS). This transformation has given rise to cybersecurity concerns, among which data poisoning attack emerges as a new threat as ITS increasingly…
Recommender systems play a crucial role in helping users to find their interested information in various web services such as Amazon, YouTube, and Google News. Various recommender systems, ranging from neighborhood-based,…
This paper proposes an online environment poisoning algorithm tailored for reinforcement learning agents operating in a black-box setting, where an adversary deliberately manipulates training data to lead the agent toward a mischievous…
The increasing access to data poses both opportunities and risks in deep learning, as one can manipulate the behaviors of deep learning models with malicious training samples. Such attacks are known as data poisoning. Recent advances in…
Gradient attacks and data poisoning tamper with the training of machine learning algorithms to maliciously alter them and have been proven to be equivalent in convex settings. The extent of harm these attacks can produce in non-convex…