273 citations · 914 across the 36 of their papers we have counts for
37 papers
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…
TMI! Finetuned Models Leak Private Information from their Pretraining Data
John Abascal, Stanley Wu, Alina Oprea +1
Transfer learning has become an increasingly popular technique in machine learning as a way to leverage a pretrained model trained for one task to assist with building a finetuned…
Unleashing the Power of Randomization in Auditing Differentially Private ML
Krishna Pillutla, Galen Andrew, Peter Kairouz +3
We present a rigorous methodology for auditing differentially private machine learning algorithms by adding multiple carefully designed examples called canaries. We take a first pr…
One-shot Empirical Privacy Estimation for Federated Learning
Galen Andrew, Peter Kairouz, Sewoong Oh +3
Privacy estimation techniques for differentially private (DP) algorithms are useful for comparing against analytical bounds, or to empirically measure privacy loss in settings wher…
Backdoor Attacks in Peer-to-Peer Federated Learning
Georgios Syros, Gokberk Yar, Simona Boboila +2
Most machine learning applications rely on centralized learning processes, opening up the risk of exposure of their training datasets. While federated learning (FL) mitigates to so…
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…
SNAP: Efficient Extraction of Private Properties with Poisoning
Harsh Chaudhari, John Abascal, Alina Oprea +3
Property inference attacks allow an adversary to extract global properties of the training dataset from a machine learning model. Such attacks have privacy implications for data ow…
Black-box Attacks Against Neural Binary Function Detection
Joshua Bundt, Michael Davinroy, Ioannis Agadakos +2
Binary analyses based on deep neural networks (DNNs), or neural binary analyses (NBAs), have become a hotly researched topic in recent years. DNNs have been wildly successful at pu…
Modeling Self-Propagating Malware with Epidemiological Models
Alesia Chernikova, Nicolò Gozzi, Simona Boboila +3
Self-propagating malware (SPM) has recently resulted in large financial losses and high social impact, with well-known campaigns such as WannaCry and Colonial Pipeline being able t…
Cyber Network Resilience against Self-Propagating Malware Attacks
Alesia Chernikova, Nicolò Gozzi, Simona Boboila +6
Self-propagating malware (SPM) has led to huge financial losses, major data breaches, and widespread service disruptions in recent years. In this paper, we explore the problem of d…
How to Combine Membership-Inference Attacks on Multiple Updated Models
Matthew Jagielski, Stanley Wu, Alina Oprea +2
A large body of research has shown that machine learning models are vulnerable to membership inference (MI) attacks that violate the privacy of the participants in the training dat…
CELEST: Federated Learning for Globally Coordinated Threat Detection
Talha Ongun, Simona Boboila, Alina Oprea +3
The cyber-threat landscape has evolved tremendously in recent years, with new threat variants emerging daily, and large-scale coordinated campaigns becoming more prevalent. In this…
SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learning
Harsh Chaudhari, Matthew Jagielski, Alina Oprea
Secure multiparty computation (MPC) has been proposed to allow multiple mutually distrustful data owners to jointly train machine learning (ML) models on their combined data. Howev…
Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis +7
The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update exi…
PORTFILER: Port-Level Network Profiling for Self-Propagating Malware Detection
Talha Ongun, Oliver Spohngellert, Benjamin Miller +7
Recent self-propagating malware (SPM) campaigns compromised hundred of thousands of victim machines on the Internet. It is challenging to detect these attacks in their early stages…
Living-Off-The-Land Command Detection Using Active Learning
Talha Ongun, Jack W. Stokes, Jonathan Bar Or +6
In recent years, enterprises have been targeted by advanced adversaries who leverage creative ways to infiltrate their systems and move laterally to gain access to critical data. O…
Adversarial Robustness Verification and Attack Synthesis in Stochastic Systems
Lisa Oakley, Alina Oprea, Stavros Tripakis
Probabilistic model checking is a useful technique for specifying and verifying properties of stochastic systems including randomized protocols and reinforcement learning models. E…
Collaborative Information Sharing for ML-Based Threat Detection
Talha Ongun, Simona Boboila, Alina Oprea +4
Recently, coordinated attack campaigns started to become more widespread on the Internet. In May 2017, WannaCry infected more than 300,000 machines in 150 countries in a few days a…
On Generating and Labeling Network Traffic with Realistic, Self-Propagating Malware
Molly Buchanan, Jeffrey W. Collyer, Jack W. Davidson +6
Research and development of techniques which detect or remediate malicious network activity require access to diverse, realistic, contemporary data sets containing labeled maliciou…
Extracting Training Data from Large Language Models
Nicholas Carlini, Florian Tramer, Eric Wallace +9
It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary ca…
Auditing Differentially Private Machine Learning: How Private is Private SGD?
Matthew Jagielski, Jonathan Ullman, Alina Oprea
We investigate whether Differentially Private SGD offers better privacy in practice than what is guaranteed by its state-of-the-art analysis. We do so via novel data poisoning atta…
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…
With Great Dispersion Comes Greater Resilience: Efficient Poisoning Attacks and Defenses for Linear Regression Models
Jialin Wen, Benjamin Zi Hao Zhao, Minhui Xue +2
With the rise of third parties in the machine learning pipeline, the service provider in "Machine Learning as a Service" (MLaaS), or external data contributors in online learning,…