Related papers: Detecting Trojaned DNNs via Spectral Regression An…

We propose and analyze an adaptive adversary that can retrain a Trojaned DNN and is also aware of SOTA output-based Trojaned model detectors. We show that such an adversary can ensure (1) high accuracy on both trigger-embedded and clean…

An emerging amount of intelligent applications have been developed with the surge of Machine Learning (ML). Deep Neural Networks (DNNs) have demonstrated unprecedented performance across various fields such as medical diagnosis and…

Deep Neural Networks (DNNs) have been shown to be susceptible to Trojan attacks. Neural Trojan is a type of targeted poisoning attack that embeds the backdoor into the victim and is activated by the trigger in the input space. The…

With the widespread use of deep neural networks (DNNs) in high-stake applications, the security problem of the DNN models has received extensive attention. In this paper, we investigate a specific security problem called trojan attack,…

This paper addresses the problem of detecting trojans in neural networks (NNs) by analyzing systematically pruned NN models. Our pruning-based approach consists of three main steps. First, detect any deviations from the reference look-up…

We target the problem of detecting Trojans or backdoors in DNNs. Such models behave normally with typical inputs but produce specific incorrect predictions for inputs poisoned with a Trojan trigger. Our approach is based on a novel…

Neural networks are powering the deployment of embedded devices and Internet of Things. Applications range from personal assistants to critical ones such as self-driving cars. It has been shown recently that models obtained from neural nets…

Deep Neural Network (DNN) classifiers are known to be vulnerable to Trojan or backdoor attacks, where the classifier is manipulated such that it misclassifies any input containing an attacker-determined Trojan trigger. Backdoors compromise…

Security of modern Deep Neural Networks (DNNs) is under severe scrutiny as the deployment of these models become widespread in many intelligence-based applications. Most recently, DNNs are attacked through Trojan which can effectively…

Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show that these training-time vulnerabilities extend to deep…

We propose CLEANN, the first end-to-end framework that enables online mitigation of Trojans for embedded Deep Neural Network (DNN) applications. A Trojan attack works by injecting a backdoor in the DNN while training; during inference, the…

In the exciting generative AI era, the diffusion model has emerged as a very powerful and widely adopted content generation and editing tool for various data modalities, making the study of their potential security risks very necessary and…

Backdoor (Trojan) attacks are an important type of adversarial exploit against deep neural networks (DNNs), wherein a test instance is (mis)classified to the attacker's target class whenever the attacker's backdoor trigger is present. In…

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…

Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of pre-trained language models (PLMs) to specific tasks. By tuning only a minimal set of (extra) parameters, PEFT achieves performance that is comparable to standard…

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…

Continual Learning with Pre-trained Models holds great promise for efficient adaptation across sequential tasks. However, most existing approaches freeze PTMs and rely on auxiliary modules like prompts or adapters, limiting model plasticity…

Deep neural networks (DNNs) are vulnerable to "backdoor" poisoning attacks, in which an adversary implants a secret trigger into an otherwise normally functioning model. Detection of backdoors in trained models without access to the…

As large language models (LLMs) become integrated into sensitive workflows, concerns grow over their potential to leak confidential information. We propose TrojanStego, a novel threat model in which an adversary fine-tunes an LLM to embed…

As deep neural networks and the datasets used to train them get larger, the default approach to integrating them into research and commercial projects is to download a pre-trained model and fine tune it. But these models can have uncertain…