Related papers: Mitigating Gradient Inversion Risks in Language Mo…

Deep neural networks are known to be vulnerable to adversarial perturbations, which are small and carefully crafted inputs that lead to incorrect predictions. In this paper, we propose DeepDefense, a novel defense framework that applies…

Federated Unlearning (FU) has emerged as a critical compliance mechanism for data privacy regulations, requiring unlearned clients to provide verifiable Proof of Federated Unlearning (PoFU) to auditors upon data removal requests. However,…

Gradient inversion attacks on federated learning systems reconstruct client training data from exchanged gradient information. To defend against such attacks, a variety of defense mechanisms were proposed. However, they usually lead to an…

Deep Neural Networks (DNNs) are well-known to be vulnerable to Adversarial Examples (AEs). A large amount of efforts have been spent to launch and heat the arms race between the attackers and defenders. Recently, advanced gradient-based…

Federated learning synchronizes models through gradient transmission and aggregation. However, these gradients pose significant privacy risks, as sensitive training data is embedded within them. Existing gradient inversion attacks suffer…

Collaborative training of neural networks leverages distributed data by exchanging gradient information between different clients. Although training data entirely resides with the clients, recent work shows that training data can be…

Federated learning (FL) has emerged as a privacy-preserving machine learning approach where multiple parties share gradient information rather than original user data. Recent work has demonstrated that gradient inversion attacks can exploit…

Federated learning has emerged as a prominent privacy-preserving technique for leveraging large-scale distributed datasets by sharing gradients instead of raw data. However, recent studies indicate that private training data can still be…

The prominence of embodied Artificial Intelligence (AI), which empowers robots to navigate, perceive, and engage within virtual environments, has attracted significant attention, owing to the remarkable advances in computer vision and large…

We propose Gradient Inversion Transcript (GIT), a novel generative approach for reconstructing training data from leaked gradients. GIT employs a generative attack model, whose architecture is tailored to align with the structure of the…

Most existing methods to detect backdoored machine learning (ML) models take one of the two approaches: trigger inversion (aka. reverse engineer) and weight analysis (aka. model diagnosis). In particular, the gradient-based trigger…

Machine learning algorithms are vulnerable to data poisoning attacks. Prior taxonomies that focus on specific scenarios, e.g., indiscriminate or targeted, have enabled defenses for the corresponding subset of known attacks. Yet, this…

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…

Model stealing attack is increasingly threatening the confidentiality of machine learning models deployed in the cloud. Recent studies reveal that adversaries can exploit data synthesis techniques to steal machine learning models even in…

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…

Graph neural networks (GNNs) have become instrumental in diverse real-world applications, offering powerful graph learning capabilities for tasks such as social networks and medical data analysis. Despite their successes, GNNs are…

Model inversion attacks (MIAs) aim to reconstruct class-representative samples from trained models. Recent generative MIAs utilize generative adversarial networks to learn image priors that guide the inversion process, yielding…

With the flourishing prosperity of generative models, manipulated facial images have become increasingly accessible, raising concerns regarding privacy infringement and societal trust. In response, proactive defense strategies embed…

Recent works on personalized text-to-image generation usually learn to bind a special token with specific subjects or styles of a few given images by tuning its embedding through gradient descent. It is natural to question whether we can…

Gradient inversion attack enables recovery of training samples from model gradients in federated learning (FL), and constitutes a serious threat to data privacy. To mitigate this vulnerability, prior work proposed both principled defenses…