Related papers: You Autocomplete Me: Poisoning Vulnerabilities in …

Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners…

The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output…

Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to…

Coding is an integral aspect of programming. A programmer can automatically complete a code fragment after writing a few tokens, and the process of automatic completion is known as code completion. Several research studies on code…

This demo paper examines the susceptibility of Federated Learning (FL) systems to targeted data poisoning attacks, presenting a novel system for visualizing and mitigating such threats. We simulate targeted data poisoning attacks via label…

In this work, we investigate the concept of biometric backdoors: a template poisoning attack on biometric systems that allows adversaries to stealthily and effortlessly impersonate users in the long-term by exploiting the template update…

This paper investigates some of the risks introduced by "LLM poisoning," the intentional or unintentional introduction of malicious or biased data during model training. We demonstrate how a seemingly improved LLM, fine-tuned on a limited…

Data poisoning attacks compromise the integrity of machine-learning models by introducing malicious training samples to influence the results during test time. In this work, we investigate backdoor data poisoning attack on deep neural…

Recent studies have shown that deep learning models are very vulnerable to poisoning attacks. Many defense methods have been proposed to address this issue. However, traditional poisoning attacks are not as threatening as commonly believed.…

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…

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…

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…

Poisoning attacks pose an increasing threat to the security and robustness of Artificial Intelligence systems in the military domain. The widespread use of open-source datasets and pretrained models exacerbates this risk. Despite the…

Code completion plays a prominent role in modern integrated development environments (IDEs). Machine learning has become ubiquitous in analogous natural language writing and search software, surfacing more relevant autocompletions and…

Adversarial training instances can severely distort a model's behavior. This work investigates certified regression defenses, which provide guaranteed limits on how much a regressor's prediction may change under a poisoning attack. Our key…

Various attack methods against recommender systems have been proposed in the past years, and the security issues of recommender systems have drawn considerable attention. Traditional attacks attempt to make target items recommended to as…

In a \emph{data poisoning attack}, an attacker modifies, deletes, and/or inserts some training examples to corrupt the learnt machine learning model. \emph{Bootstrap Aggregating (bagging)} is a well-known ensemble learning method, which…

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…

Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the…

Under a commonly-studied backdoor poisoning attack against classification models, an attacker adds a small trigger to a subset of the training data, such that the presence of this trigger at test time causes the classifier to always predict…