Related papers: Regularisation Can Mitigate Poisoning Attacks: A N…
Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning from a large-scale unlabeled dataset also exposes the model…
Machine learning (ML) models trained on data from potentially untrusted sources are vulnerable to poisoning. A small, maliciously crafted subset of the training inputs can cause the model to learn a "backdoor" task (e.g., misclassify inputs…
Fair machine learning seeks to mitigate model prediction bias against certain demographic subgroups such as elder and female. Recently, fair representation learning (FRL) trained by deep neural networks has demonstrated superior…
The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…
Machine learning models trained on data from the outside world can be corrupted by data poisoning attacks that inject malicious points into the models' training sets. A common defense against these attacks is data sanitization: first filter…
Liver infection is a common disease, which poses a great threat to human health, but there is still able to identify an optimal technique that can be used on large-level screening. This paper deals with ML algorithms using different data…
Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…
Data poisoning attacks, in which an adversary corrupts a training set with the goal of inducing specific desired mistakes, have raised substantial concern: even just the possibility of such an attack can make a user no longer trust the…
Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoning assuming adversaries control a percentage of the training…
Data poisoning -- the process by which an attacker takes control of a model by making imperceptible changes to a subset of the training data -- is an emerging threat in the context of neural networks. Existing attacks for data poisoning…
Ensuring the reliability of machine learning-based intrusion detection systems remains a critical challenge in Internet of Things (IoT) environments, particularly as data poisoning attacks increasingly threaten the integrity of model…
Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications. While a body of…
Meta-learning models have two objectives. First, they need to be able to make predictions over a range of task distributions while utilizing only a small amount of training data. Second, they also need to adapt to new novel unseen tasks at…
Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning attacks, the attacker reduces the model's performance on…
Automated hyperparameter search in machine learning, especially for deep learning models, is typically formulated as a bilevel optimization problem, with hyperparameter values determined by the upper level and the model learning achieved by…
Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However, the existence of adversarial attacks and data poisoning…
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…
Reinforcement learning (RL) is an actively growing field that is seeing increased usage in real-world, safety-critical applications -- making it paramount to ensure the robustness of RL algorithms against adversarial attacks. In this work…
Reinforcement learning (RL) has achieved phenomenal success in various domains. However, its data-driven nature also introduces new vulnerabilities that can be exploited by malicious opponents. Recent work shows that a well-trained RL agent…
Instance-targeted data poisoning attacks, where an adversary corrupts a training set to induce errors on specific test points, have raised significant concerns. Balcan et al (2022) proposed an approach to addressing this challenge by…