Andrew A. Mahyari

Kyle Stein, Andrew A. Mahyari, Guillermo Francia et al.

As the complexity and connectivity of networks increase, the need for novel malware detection approaches becomes imperative. Traditional security defenses are becoming less effective against the advanced tactics of today's cyberattacks. Deep Packet Inspection (DPI) has emerged as a key technology in strengthening network security, offering detailed analysis of network traffic that goes beyond simple metadata analysis. DPI examines not only the packet headers but also the payload content within, offering a thorough insight into the data traversing the network. This study proposes a novel approach that leverages a large language model (LLM) and few-shot learning to accurately recognizes novel, unseen malware types with few labels samples. Our proposed approach uses a pretrained LLM on known malware types to extract the embeddings from packets. The embeddings are then used alongside few labeled samples of an unseen malware type. This technique is designed to acclimate the model to different malware representations, further enabling it to generate robust embeddings for each trained and unseen classes. Following the extraction of embeddings from the LLM, few-shot learning is utilized to enhance performance with minimal labeled data. Our evaluation, which utilized two renowned datasets, focused on identifying malware types within network traffic and Internet of Things (IoT) environments. Our approach shows promising results with an average accuracy of 86.35% and F1-Score of 86.40% on different malware types across the two datasets.

Arash Raftari, Mehrdad Mahdavi, Nathan Blackthorn et al.

Backdoor attacks pose a serious threat to large language models (LLMs) by causing otherwise benign systems to produce attacker-specified malicious behavior when a hidden trigger is present. In this work, we study post hoc detoxification of backdoored LLMs in a practical setting where the defender has access to the poisoned model but does not wish to retrain the full network from scratch. We propose a mechanistically guided weight-space repair framework that first localizes modules involved in propagating trigger-induced behavior using activation patching and Fisher/K-FAC curvature analysis, and then applies targeted low-rank repair to only the most influential modules. We evaluate the method on poisoned variants of \texttt{Llama-3.2-1B-Instruct} with triggers inserted at the beginning, middle, and end of otherwise benign prompts. Results show that the proposed approach substantially suppresses trigger-conditioned malicious responses while preserving benign model behavior. These findings suggest that backdoor removal in LLMs can be formulated as a localized structural repair problem rather than only a broad behavioral alignment problem.

Kyle Stein, Andrew A. Mahyari, Guillermo Francia et al.

One-shot learning focuses on adapting pretrained models to recognize newly introduced and unseen classes based on a single labeled image. While variations of few-shot and zero-shot learning exist, one-shot learning remains a challenging yet crucial problem due to its ability to generalize knowledge to unseen classes from just one human-annotated image. In this paper, we introduce a transductive one-shot learning approach that employs subspace decomposition to utilize the information from labeled images in the support set and unlabeled images in the query set. These images are decomposed into a linear combination of latent variables representing primitives captured by smaller subspaces. By representing images in the query set as linear combinations of these latent primitives, we can propagate the label from a single image in the support set to query images that share similar combinations of primitives. Through a comprehensive quantitative analysis across various neural network feature extractors and datasets, we demonstrate that our approach can effectively generalize to novel classes from just one labeled image.

Kyle Stein, Andrew Arash Mahyari, Guillermo Francia et al.

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through weight fine-tuning, much less attention has been given to detecting backdoored samples directly. Given the vast datasets used in training, manual inspection for backdoor triggers is impractical, and even state-of-the-art defense mechanisms fail to fully neutralize their impact. To address this gap, we introduce a groundbreaking method to detect unseen backdoored images during both training and inference. Leveraging the transformative success of prompt tuning in Vision Language Models (VLMs), our approach trains learnable text prompts to differentiate clean images from those with hidden backdoor triggers. Experiments demonstrate the exceptional efficacy of this method, achieving an impressive average accuracy of 86% across two renowned datasets for detecting unseen backdoor triggers, establishing a new standard in backdoor defense.

Kyle Stein, Andrew A. Mahyari, Guillermo Francia et al.

Deep neural networks (DNNs) and generative AI (GenAI) are increasingly vulnerable to backdoor attacks, where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels. Beyond traditional single-trigger scenarios, attackers may inject multiple triggers across various object classes, forming unseen backdoor-object configurations that evade standard detection pipelines. In this paper, we introduce DBOM (Disentangled Backdoor-Object Modeling), a proactive framework that leverages structured disentanglement to identify and neutralize both seen and unseen backdoor threats at the dataset level. Specifically, DBOM factorizes input image representations by modeling triggers and objects as independent primitives in the embedding space through the use of Vision-Language Models (VLMs). By leveraging the frozen, pre-trained encoders of VLMs, our approach decomposes the latent representations into distinct components through a learnable visual prompt repository and prompt prefix tuning, ensuring that the relationships between triggers and objects are explicitly captured. To separate trigger and object representations in the visual prompt repository, we introduce the trigger-object separation and diversity losses that aids in disentangling trigger and object visual features. Next, by aligning image features with feature decomposition and fusion, as well as learned contextual prompt tokens in a shared multimodal space, DBOM enables zero-shot generalization to novel trigger-object pairings that were unseen during training, thereby offering deeper insights into adversarial attack patterns. Experimental results on CIFAR-10 and GTSRB demonstrate that DBOM robustly detects poisoned images prior to downstream training, significantly enhancing the security of DNN training pipelines.