Private Statistical Estimation Via Truncation

We introduce a novel framework for differentially private DP statistical estimation via data truncation, addressing a key challenge in DP estimation when the data support is unbounded. Traditional approaches rely on problem-specific sensitivity analysis, limiting their applicability. By leveragin...

Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent

As Large Language Models LLMs are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from human feedback RLHF, they are still vulnerable to jailbreakin...

Manipulating Machine-Learning Systems through the Order of the Training Data

Yet another adversarial ML attack: Most deep neural networks are trained by stochastic gradient descent. Now “stochastic” is a fancy Greek word for “random”; it means that the training data are fed into the model in random order. So what happens if the bad guys can cause the order to be not rando...

Fedora: Security Advisory for python-sport-activities-features (FEDORA-2021-f5fea1fbd3)

The remote host is missing an update for the SPDX-FileCopyrightText: 2021 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only ifdescription...

Machine learning classifiers trained via gradient descent are vulnerable to arbitrary misclassification attack

Overview Machine learning models trained using gradient descent can be forced to make arbitrary misclassifications by an attacker that can influence the items to be classified. The impact of a misclassification varies widely depending on the ML model's purpose and of what systems it is a part...