相关论文: Hide in Plain Sight: Clean-Label Backdoor for Audi…

Membership inference attack is one of the most popular privacy attacks in machine learning, which aims to predict whether a given sample was contained in the target model's training set. Label-only membership inference attack is a variant…

Synthetic data is seen as the most promising solution to share individual-level data while preserving privacy. Shadow modeling-based Membership Inference Attacks (MIAs) have become the standard approach to evaluate the privacy risk of…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Deep learning models are vulnerable to backdoor attacks, where attackers inject malicious behavior through data poisoning and later exploit triggers to manipulate deployed models. To improve the stealth and effectiveness of backdoors, prior…

The vulnerability of machine learning models to Membership Inference Attacks (MIAs) has garnered considerable attention in recent years. These attacks determine whether a data sample belongs to the model's training set or not. Recent…

In the domain of backdoor attacks, accurate labeling of injected data is essential for evading rudimentary detection mechanisms. This imperative has catalyzed the development of clean-label attacks, which are notably more elusive as they…

With the emergence of powerful large-scale foundation models, the training paradigm is increasingly shifting from from-scratch training to transfer learning. This enables high utility training with small, domain-specific datasets typical in…

Large Reasoning Models (LRMs) have rapidly gained prominence for their strong performance in solving complex tasks. Many modern black-box LRMs expose the intermediate reasoning traces through APIs to improve transparency (e.g., Gemini-2.5…

Video large language models (VideoLLMs) are increasingly trained or instruction-tuned on large-scale video--text corpora collected from heterogeneous sources, raising an immediate privacy question: can an external auditor determine whether…

Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clean-label settings…

Membership Inference Attacks exploit the vulnerabilities of exposing models trained on customer data to queries by an adversary. In a recently proposed implementation of an auditing tool for measuring privacy leakage from sensitive…

Diffusion models have demonstrated remarkable capabilities in image synthesis, but their recently proven vulnerability to Membership Inference Attacks (MIAs) poses a critical privacy concern. This paper introduces two novel and efficient…

Federated Learning (FL) is an emerging solution to the data scarcity problem for training deep learning models in hardware assurance. While FL is designed to enhance privacy by not sharing raw data, it remains vulnerable to Membership…

Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted approaches by a wide margin. Motivated by this observation, we address the following question: can the…

Machine unlearning updates machine learning models to remove information from specific training samples, complying with data protection regulations that allow individuals to request the removal of their personal data. Despite the recent…

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…

Machine learning (ML) models have been shown to be vulnerable to Membership Inference Attacks (MIA), which infer the membership of a given data point in the target dataset by observing the prediction output of the ML model. While the key…

To gather a significant quantity of annotated training data for high-performance image classification models, numerous companies opt to enlist third-party providers to label their unlabeled data. This practice is widely regarded as secure,…

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…