Related papers: Towards Stable Backdoor Purification through Featu…

Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks, which brings a huge security risk to the further application of DNNs, especially for the AI models developed in the real world.…

The goal of federated learning (FL) is to train one global model by aggregating model parameters updated independently on edge devices without accessing users' private data. However, FL is susceptible to backdoor attacks where a small…

Data poisoning attacks and backdoor attacks aim to corrupt a machine learning classifier via modifying, adding, and/or removing some carefully selected training examples, such that the corrupted classifier makes incorrect predictions as the…

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…

As fine-tuning large language models (LLMs) becomes increasingly prevalent, users often rely on third-party services with limited visibility into their fine-tuning processes. This lack of transparency raises the question: how do consumers…

Third-party resources ($e.g.$, samples, backbones, and pre-trained models) are usually involved in the training of deep neural networks (DNNs), which brings backdoor attacks as a new training-phase threat. In general, backdoor attackers…

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

Deep neural networks are susceptible to backdoor attacks, where adversaries manipulate model predictions by inserting malicious samples into the training data. Currently, there is still a significant challenge in identifying suspicious…

Backdoors and adversarial examples are the two primary threats currently faced by deep neural networks (DNNs). Both attacks attempt to hijack the model behaviors with unintended outputs by introducing (small) perturbations to the inputs.…

In this paper we investigate the frequency sensitivity of Deep Neural Networks (DNNs) when presented with clean samples versus poisoned samples. Our analysis shows significant disparities in frequency sensitivity between these two types of…

Data poisoning and backdoor attacks manipulate training data to induce security breaches in a victim model. These attacks can be provably deflected using differentially private (DP) training methods, although this comes with a sharp…

Deep neural networks (DNNs) are state-of-the-art algorithms for multiple applications, spanning from image classification to speech recognition. While providing excellent accuracy, they often have enormous compute and memory requirements.…

Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a…

In the rapidly evolving landscape of communication and network security, the increasing reliance on deep neural networks (DNNs) and cloud services for data processing presents a significant vulnerability: the potential for backdoors that…

We present a novel defense, against backdoor attacks on Deep Neural Networks (DNNs), wherein adversaries covertly implant malicious behaviors (backdoors) into DNNs. Our defense falls within the category of post-development defenses that…

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

Multimodal Diffusion Language Models (MDLMs) have recently emerged as a competitive alternative to their autoregressive counterparts. Yet their vulnerability to backdoor attacks remains largely unexplored. In this work, we show that…

Deep neural networks (DNNs) play an important role in machine learning due to its outstanding performance compared to other alternatives. However, DNNs are not suitable for safety-critical applications since DNNs can be easily fooled by…

Deep neural networks (DNNs) have become one of the enabling technologies in many safety-critical applications, e.g., autonomous driving and medical image analysis. DNN systems, however, suffer from various kinds of threats, such as…

Backdoor attack has emerged as a major security threat to deep neural networks (DNNs). While existing defense methods have demonstrated promising results on detecting or erasing backdoors, it is still not clear whether robust training…