Related papers: Poisoning Attacks against Data-Driven Control Meth…

Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this…

Model adaptation tackles the distribution shift problem with a pre-trained model instead of raw data, which has become a popular paradigm due to its great privacy protection. Existing methods always assume adapting to a clean target domain,…

While state-of-the-art diffusion models (DMs) excel in image generation, concerns regarding their security persist. Earlier research highlighted DMs' vulnerability to data poisoning attacks, but these studies placed stricter requirements…

Semi-supervised Federated Learning (SSFL) has recently drawn much attention due to its practical consideration, i.e., the clients may only have unlabeled data. In practice, these SSFL systems implement semi-supervised training by assigning…

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…

Indiscriminate data poisoning attacks are quite effective against supervised learning. However, not much is known about their impact on unsupervised contrastive learning (CL). This paper is the first to consider indiscriminate poisoning…

Data poisoning has been proposed as a compelling defense against facial recognition models trained on Web-scraped pictures. Users can perturb images they post online, so that models will misclassify future (unperturbed) pictures. We…

In this paper, we investigate how to manipulate the coefficients obtained via linear regression by adding carefully designed poisoning data points to the dataset or modify the original data points. Given the energy budget, we first provide…

Despite their tremendous success in a range of domains, deep learning systems are inherently susceptible to two types of manipulations: adversarial inputs -- maliciously crafted samples that deceive target deep neural network (DNN) models,…

Genomic foundation models trained on DNA sequences have demonstrated remarkable capabilities across diverse biological tasks, from variant effect prediction to genome design. These models are typically trained on massive, publicly sourced…

Model poisoning attacks on federated learning (FL) intrude in the entire system via compromising an edge model, resulting in malfunctioning of machine learning models. Such compromised models are tampered with to perform adversary-desired…

AI-based code generators have become pivotal in assisting developers in writing software starting from natural language (NL). However, they are trained on large amounts of data, often collected from unsanitized online sources (e.g., GitHub,…

This paper is concerned with understanding and countering the effects of database attacks on a learning-based linear quadratic adaptive controller. This attack targets neither sensors nor actuators, but just poisons the learning algorithm…

As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor…

Data-oriented attacks manipulate non-control data to alter a program's benign behavior without violating its control-flow integrity. It has been shown that such attacks can cause significant damage even in the presence of control-flow…

Poisoning attacks are a primary threat to machine learning models, aiming to compromise their performance and reliability by manipulating training datasets. This paper introduces a novel attack - Outlier-Oriented Poisoning (OOP) attack,…

Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…

As the complexities of Dynamic Data Driven Applications Systems increase, preserving their resilience becomes more challenging. For instance, maintaining power grid resilience is becoming increasingly complicated due to the growing number…

Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…

One of the most concerning threats for modern AI systems is data poisoning, where the attacker injects maliciously crafted training data to corrupt the system's behavior at test time. Availability poisoning is a particularly worrisome…