research
∙
09/04/2023
Dropout Attacks
Dropout is a common operator in deep learning, aiming to prevent overfit...
share
research
∙
06/02/2023
Poisoning Network Flow Classifiers
As machine learning (ML) classifiers increasingly oversee the automated ...
research
∙
06/01/2023
TMI! Finetuned Models Leak Private Information from their Pretraining Data
Transfer learning has become an increasingly popular technique in machin...
research
∙
05/29/2023
Unleashing the Power of Randomization in Auditing Differentially Private ML
We present a rigorous methodology for auditing differentially private ma...
research
∙
02/06/2023
One-shot Empirical Privacy Estimation for Federated Learning
Privacy auditing techniques for differentially private (DP) algorithms a...
research
∙
01/23/2023
Backdoor Attacks in Peer-to-Peer Federated Learning
We study backdoor attacks in peer-to-peer federated learning systems on ...
research
∙
10/06/2022
Bad Citrus: Reducing Adversarial Costs with Model Distances
Recent work by Jia et al., showed the possibility of effectively computi...
research
∙
08/27/2022
Network-Level Adversaries in Federated Learning
Federated learning is a popular strategy for training models on distribu...
research
∙
08/25/2022
SNAP: Efficient Extraction of Private Properties with Poisoning
Property inference attacks allow an adversary to extract global properti...
research
∙
08/24/2022
Attacking Neural Binary Function Detection
Binary analyses based on deep neural networks (DNNs), or neural binary a...
research
∙
08/05/2022
Modeling Self-Propagating Malware with Epidemiological Models
Self-propagating malware (SPM) has recently resulted in large financial ...
research
∙
06/27/2022
Cyber Network Resilience against Self-Propagating Malware Attacks
Self-propagating malware (SPM) has led to huge financial losses, major d...
research
∙
05/23/2022
CELEST: Federated Learning for Globally Coordinated Threat Detection
The cyber-threat landscape has evolved tremendously in recent years, wit...
research
∙
05/20/2022
SafeNet: Mitigating Data Poisoning Attacks on Private Machine Learning
Secure multiparty computation (MPC) has been proposed to allow multiple ...
research
∙
05/12/2022
How to Combine Membership-Inference Attacks on Multiple Updated Models
A large body of research has shown that machine learning models are vuln...
research
∙
12/27/2021
PORTFILER: Port-Level Network Profiling for Self-Propagating Malware Detection
Recent self-propagating malware (SPM) campaigns compromised hundred of t...
research
∙
11/30/2021
Living-Off-The-Land Command Detection Using Active Learning
In recent years, enterprises have been targeted by advanced adversaries ...
research
∙
10/05/2021
Adversarial Robustness Verification and Attack Synthesis in Stochastic Systems
Probabilistic model checking is a useful technique for specifying and ve...
research
∙
04/23/2021
Collaborative Information Sharing for ML-Based Threat Detection
Recently, coordinated attack campaigns started to become more widespread...
research
∙
04/20/2021
On Generating and Labeling Network Traffic with Realistic, Self-Propagating Malware
Research and development of techniques which detect or remediate malicio...
research
∙
12/14/2020
Extracting Training Data from Large Language Models
It has become common to publish large (billion parameter) language model...
research
∙
06/24/2020
Subpopulation Data Poisoning Attacks
Machine learning (ML) systems are deployed in critical settings, but the...
research
∙
06/13/2020
Auditing Differentially Private Machine Learning: How Private is Private SGD?
We investigate whether Differentially Private SGD offers better privacy ...
research
∙
03/02/2020
Exploring Backdoor Poisoning Attacks Against Malware Classifiers
Current training pipelines for machine learning (ML) based malware class...
research
∙
09/23/2019
Adversarial Examples for Deep Learning Cyber Security Analytics
As advances in Deep Neural Networks demonstrate unprecedented levels of ...
research
∙
08/06/2019
AppMine: Behavioral Analytics for Web Application Vulnerability Detection
Web applications in widespread use have always been the target of large-...
research
∙
08/01/2019
The House That Knows You: User Authentication Based on IoT Data
Home-based Internet of Things (IoT) devices have gained in popularity an...
research
∙
07/10/2019
On Designing Machine Learning Models for Malicious Network Traffic Classification
Machine learning (ML) started to become widely deployed in cyber securit...
research
∙
06/27/2019
QFlip: An Adaptive Reinforcement Learning Strategy for the FlipIt Security Game
A rise in Advanced Persistent Threats (APTs) has introduced a need for r...
research
∙
06/27/2019
Playing Adaptively Against Stealthy Opponents: A Reinforcement Learning Strategy for the FlipIt Security Game
A rise in Advanced Persistant Threats (APTs) has introduced a need for r...
research
∙
04/15/2019
Are Self-Driving Cars Secure? Evasion Attacks against Deep Neural Networks for Steering Angle Prediction
Deep Neural Networks (DNNs) have tremendous potential in advancing the v...
research
∙
04/09/2019
Privacy-Preserving Hierarchical Clustering: Formal Security and Efficient Approximation
Machine Learning (ML) is widely used for predictive tasks in a number of...
research
∙
12/06/2018
Differentially Private Fair Learning
We design two learning algorithms that simultaneously promise differenti...
research
∙
09/08/2018
On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks
Transferability captures the ability of an attack against a machine-lear...
research
∙
04/01/2018
Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
As machine learning becomes widely used for automated decisions, attacke...
research
∙
08/07/2016