Related papers: Do Not Return Similarity: Face Recovery with Dista…

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

With the widespread application of artificial intelligence technologies in face recognition and other fields, data privacy security issues have received extensive attention, especially the \textit{right to be forgotten} emphasized by…

Inverting visual representations within deep neural networks (DNNs) presents a challenging and important problem in the field of security and privacy for deep learning. The main goal is to invert the features of an unidentified target image…

While being deployed in many critical applications as core components, machine learning (ML) models are vulnerable to various security and privacy attacks. One major privacy attack in this domain is membership inference, where an adversary…

Federated learning is a decentralized learning paradigm introduced to preserve privacy of client data. Despite this, prior work has shown that an attacker at the server can still reconstruct the private training data using only the client…

Artificial intelligence (AI) has been a topic of major research for many years. Especially, with the emergence of deep neural network (DNN), these studies have been tremendously successful. Today machines are capable of making faster, more…

LLM safety evaluations predominantly test models in isolation, yet deployed AI agents increasingly operate within persistent social environments alongside other agents. We introduce a Moltbook-style simulation platform where thousands of…

The application of machine learning (ML) in computer systems introduces not only many benefits but also risks to society. In this paper, we develop the concept of ML governance to balance such benefits and risks, with the aim of achieving…

Metric differential privacy (mDP) strengthens local differential privacy (LDP) by scaling noise to semantic distance, but many machine learning (ML) systems are consumed under joint observation, where model-agnostic, per-record guarantees…

Modern computer vision services often require users to share raw feature descriptors with an untrusted server. This presents an inherent privacy risk, as raw descriptors may be used to recover the source images from which they were…

Reproducibility is a cornerstone of scientific research, enabling independent verification and validation of empirical findings. The topic gained prominence in fields such as psychology and medicine, where concerns about non - replicable…

Federated Learning (FL) enables collaborative model building among a large number of participants without the need for explicit data sharing. But this approach shows vulnerabilities when privacy inference attacks are applied to it. In…

Recent works have demonstrated the feasibility of inverting face recognition systems, enabling to recover convincing face images using only their embeddings. We leverage such template inversion models to develop a novel type ofdeep morphing…

In privacy-preserving machine learning, it is common that the owner of the learned model does not have any physical access to the data. Instead, only a secured remote access to a data lake is granted to the model owner without any ability…

For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world…

With the increasing adoption of AI, inherent security and privacy vulnerabilities formachine learning systems are being discovered. One such vulnerability makes itpossible for an adversary to obtain private information about the types of…

Ensuring the privacy of research participants is vital, even more so in healthcare environments. Deep learning approaches to neuroimaging require large datasets, and this often necessitates sharing data between multiple sites, which is…

The growth of low-end hardware has led to a proliferation of machine learning-based services in edge applications. These applications gather contextual information about users and provide some services, such as personalized offers, through…

With the recent advancements in machine learning theory, many commercial embedded micro-processors use neural network models for a variety of signal processing applications. However, their associated side-channel security vulnerabilities…

Large Language Models for Code (LLMs4Code) have achieved strong performance in code generation, but recent studies reveal that they may memorize and leak sensitive information contained in training data, posing serious privacy risks. To…