Related papers: A Separation Result Between Data-oblivious and Dat…

Adversarial attacks alter NLP model predictions by perturbing test-time inputs. However, it is much less understood whether, and how, predictions can be manipulated with small, concealed changes to the training data. In this work, we…

We propose a novel clustering mechanism based on an incompatibility property between subsets of data that emerges during model training. This mechanism partitions the dataset into subsets that generalize only to themselves, i.e., training…

We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…

Adversarial attacks by malicious actors on machine learning systems, such as introducing poison triggers into training datasets, pose significant risks. The challenge in resolving such an attack arises in practice when only a subset of the…

Most recent studies have shown several vulnerabilities to attacks with the potential to jeopardize the integrity of the model, opening in a few recent years a new window of opportunity in terms of cyber-security. The main interest of this…

Machine learning has become one of the main components for task automation in many application domains. Despite the advancements and impressive achievements of machine learning, it has been shown that learning algorithms can be compromised…

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…

Machine Learning (ML) algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to deliberately degrade the algorithms' performance. Optimal poisoning attacks, which can be formulated as bilevel…

Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning…

Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third party or resort to publicly available pre-trained models.…

Consider the task of learning a hypothesis class $\mathcal{H}$ in the presence of an adversary that can replace up to an $\eta$ fraction of the examples in the training set with arbitrary adversarial examples. The adversary aims to fail the…

Deep learning models are vulnerable to various adversarial manipulations of their training data, parameters, and input sample. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model,…

To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that…

Poisoning attacks, in which an attacker adversarially manipulates the training dataset of a machine learning (ML) model, pose a significant threat to ML security. Beta Poisoning is a recently proposed poisoning attack that disrupts model…

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…

Similar to other machine learning frameworks, Offline Reinforcement Learning (RL) is shown to be vulnerable to poisoning attacks, due to its reliance on externally sourced datasets, a vulnerability that is exacerbated by its sequential…

In federated learning, multiple client devices jointly learn a machine learning model: each client device maintains a local model for its local training dataset, while a master device maintains a global model via aggregating the local…

Unlearnable example attacks are data poisoning techniques that can be used to safeguard public data against unauthorized use for training deep learning models. These methods add stealthy perturbations to the original image, thereby making…

Data poisoning attacks manipulate training data to introduce unexpected behaviors into machine learning models at training time. For text-to-image generative models with massive training datasets, current understanding of poisoning attacks…

Data poisoning attacks are a potential threat to machine learning (ML) models, aiming to manipulate training datasets to disrupt their performance. Existing defenses are mostly designed to mitigate specific poisoning attacks or are aligned…