Related papers: Mudjacking: Patching Backdoor Vulnerabilities in F…

Model extraction attacks are one type of inference-time attacks that approximate the functionality and performance of a black-box victim model by launching a certain number of queries to the model and then leveraging the model's predictions…

Machine learning backdoors have the property that the machine learning model should work as expected on normal inputs, but when the input contains a specific $\textit{trigger}$, it behaves as the attacker desires. Detecting such triggers…

Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards…

Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditional static and…

While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…

Despite the transformative impact of deep learning across multiple domains, the inherent opacity of these models has driven the development of Explainable Artificial Intelligence (XAI). Among these efforts, Concept Bottleneck Models (CBMs)…

We propose a minimax formulation for removing backdoors from a given poisoned model based on a small set of clean data. This formulation encompasses much of prior work on backdoor removal. We propose the Implicit Bacdoor Adversarial…

As ML models become increasingly complex and integral to high-stakes domains such as finance and healthcare, they also become more susceptible to sophisticated adversarial attacks. We investigate the threat posed by undetectable backdoors,…

We conduct a systematic study of backdoor vulnerabilities in normally trained Deep Learning models. They are as dangerous as backdoors injected by data poisoning because both can be equally exploited. We leverage 20 different types of…

The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies. However, this openness also brings significant security risks, including…

Artificial Intelligence (AI) has made incredible progress recently. On the one hand, advanced foundation models like ChatGPT can offer powerful conversation, in-context learning and code generation abilities on a broad range of open-domain…

Federated learning allows clients to collaboratively train a global model without uploading raw data for privacy preservation. This feature, i.e., the inability to review participants' datasets, has recently been found responsible for…

Machine Learning using neural networks has received prominent attention recently because of its success in solving a wide variety of computational tasks, in particular in the field of computer vision. However, several works have drawn…

Backdoor learning is a critical research topic for understanding the vulnerabilities of deep neural networks. While the diffusion model (DM) has been broadly deployed in public over the past few years, the understanding of its backdoor…

The increasing adoption of 3D point cloud data in various applications, such as autonomous vehicles, robotics, and virtual reality, has brought about significant advancements in object recognition and scene understanding. However, this…

This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence (AI) models. The motivation comes from our lack of understanding and the implications of using cryptographic techniques for…

Medical foundation models are gaining prominence in the medical community for their ability to derive general representations from extensive collections of medical image-text pairs. Recent research indicates that these models are…

Federated learning allows multiple users to collaboratively train a shared classification model while preserving data privacy. This approach, where model updates are aggregated by a central server, was shown to be vulnerable to poisoning…

The backdoor attack, where the adversary uses inputs stamped with triggers (e.g., a patch) to activate pre-planted malicious behaviors, is a severe threat to Deep Neural Network (DNN) models. Trigger inversion is an effective way of…

The proliferation of face forgery techniques has raised significant concerns within society, thereby motivating the development of face forgery detection methods. These methods aim to distinguish forged faces from genuine ones and have…