56 citations · 70 across the 9 of their papers we have counts for
10 papers
Model-agnostic clean-label backdoor mitigation in cybersecurity environments
Giorgio Severi, Simona Boboila, John Holodnak +4
The training phase of machine learning models is a delicate step, especially in cybersecurity contexts. Recent research has surfaced a series of insidious training-time attacks tha…
Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation
Harsh Chaudhari, Giorgio Severi, John Abascal +6
Retrieval Augmented Generation (RAG) expands the capabilities of modern large language models (LLMs), by anchoring, adapting, and personalizing their responses to the most relevant…
Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning
Harsh Chaudhari, Giorgio Severi, Alina Oprea +1
The integration of machine learning (ML) in numerous critical applications introduces a range of privacy concerns for individuals who provide their datasets for model training. One…
Privacy Side Channels in Machine Learning Systems
Edoardo Debenedetti, Giorgio Severi, Nicholas Carlini +5
Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum. Yet, in reality, these models are part of larger systems that include…
Poisoning Network Flow Classifiers
Giorgio Severi, Simona Boboila, Alina Oprea +3
As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This…
Ask and You Shall Receive (a Graph Drawing): Testing ChatGPT's Potential to Apply Graph Layout Algorithms
Sara Di Bartolomeo, Giorgio Severi, Victor Schetinger +1
Large language models (LLMs) have recently taken the world by storm. They can generate coherent text, hold meaningful conversations, and be taught concepts and basic sets of instru…
Bad Citrus: Reducing Adversarial Costs with Model Distances
Giorgio Severi, Will Pearce, Alina Oprea
Recent work by Jia et al., showed the possibility of effectively computing pairwise model distances in weight space, using a model explanation technique known as LIME. This method…
Network-Level Adversaries in Federated Learning
Giorgio Severi, Matthew Jagielski, Gökberk Yar +3
Federated learning is a popular strategy for training models on distributed, sensitive data, while preserving data privacy. Prior work identified a range of security threats on fed…
Subpopulation Data Poisoning Attacks
Matthew Jagielski, Giorgio Severi, Niklas Pousette Harger +1
Machine learning systems are deployed in critical settings, but they might fail in unexpected ways, impacting the accuracy of their predictions. Poisoning attacks against machine l…
Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers
Giorgio Severi, Jim Meyer, Scott Coull +1
Training pipelines for machine learning (ML) based malware classification often rely on crowdsourced threat feeds, exposing a natural attack injection point. In this paper, we stud…