7 papers
Curvature-Guided Module Localization for Low-Rank Detoxification of Backdoored Large Language Models
Arash Raftari, Mehrdad Mahdavi, Nathan Blackthorn +1
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…
Packet Inspection Transformer: A Self-Supervised Journey to Unseen Malware Detection with Few Samples
Kyle Stein, Arash Mahyari, Guillermo Francia +1
As networks continue to expand and become more interconnected, the need for novel malware detection methods becomes more pronounced. Traditional security measures are increasingly…
Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense
Kyle Stein, Andrew A. Mahyari, Guillermo Francia +1
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 o…
Transductive One-Shot Learning Meet Subspace Decomposition
Kyle Stein, Andrew A. Mahyari, Guillermo Francia +1
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…
Adaptive Additive Parameter Updates of Vision Transformers for Few-Shot Continual Learning
Kyle Stein, Andrew Arash Mahyari, Guillermo Francia +1
Integrating new class information without losing previously acquired knowledge remains a central challenge in artificial intelligence, often referred to as catastrophic forgetting.…
Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images
Kyle Stein, Andrew Arash Mahyari, Guillermo Francia +1
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 mit…