401 citations · 437 across the 21 of their papers we have counts for
23 papers
Efficient Storage Integrity in Adversarial Settings
Quinn Burke, Ryan Sheatsley, Yohan Beugin +4
Storage integrity is essential to systems and applications that use untrusted storage (e.g., public clouds, end-user devices). However, known methods for achieving storage integrit…
On the Robustness Tradeoff in Fine-Tuning
Kunyang Li, Jean-Charles Noirot Ferrand, Ryan Sheatsley +4
Fine-tuning has become the standard practice for adapting pre-trained models to downstream tasks. However, the impact on model robustness is not well understood. In this work, we c…
Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
Kyle Domico, Jean-Charles Noirot Ferrand, Ryan Sheatsley +3
Attacks on machine learning models have been extensively studied through stateless optimization. In this paper, we demonstrate how a reinforcement learning (RL) agent can learn a n…
Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs
Jean-Charles Noirot Ferrand, Yohan Beugin, Eric Pauley +2
Alignment in large language models (LLMs) is used to enforce guidelines such as safety. Yet, alignment fails in the face of jailbreak attacks that modify inputs to induce unsafe ou…
Err on the Side of Texture: Texture Bias on Real Data
Blaine Hoak, Ryan Sheatsley, Patrick McDaniel
Bias significantly undermines both the accuracy and trustworthiness of machine learning models. To date, one of the strongest biases observed in image classification models is text…
ParTEETor: A System for Partial Deployments of TEEs within Tor
Rachel King, Quinn Burke, Yohan Beugin +5
The Tor anonymity network allows users such as political activists and those under repressive governments to protect their privacy when communicating over the internet. At the same…
On Scalable Integrity Checking for Secure Cloud Disks
Quinn Burke, Ryan Sheatsley, Rachel King +3
Merkle hash trees are the standard method to protect the integrity and freshness of stored data. However, hash trees introduce additional compute and I/O costs on the I/O critical…
Characterizing the Modification Space of Signature IDS Rules
Ryan Guide, Eric Pauley, Yohan Beugin +2
Signature-based Intrusion Detection Systems (SIDSs) are traditionally used to detect malicious activity in networks. A notable example of such a system is Snort, which compares net…
Systematic Evaluation of Geolocation Privacy Mechanisms
Alban Héon, Ryan Sheatsley, Quinn Burke +4
Location data privacy has become a serious concern for users as Location Based Services (LBSs) have become an important part of their life. It is possible for malicious parties hav…
Securing Cloud File Systems with Trusted Execution
Quinn Burke, Yohan Beugin, Blaine Hoak +7
Cloud file systems offer organizations a scalable and reliable file storage solution. However, cloud file systems have become prime targets for adversaries, and traditional designs…
Secure IP Address Allocation at Cloud Scale
Eric Pauley, Kyle Domico, Blaine Hoak +5
Public clouds necessitate dynamic resource allocation and sharing. However, the dynamic allocation of IP addresses can be abused by adversaries to source malicious traffic, bypass…
Privacy-Preserving Protocols for Smart Cameras and Other IoT Devices
Yohan Beugin, Quinn Burke, Blaine Hoak +5
Millions of consumers depend on smart camera systems to remotely monitor their homes and businesses. However, the architecture and design of popular commercial systems require user…
Adversarial Plannning
Valentin Vie, Ryan Sheatsley, Sophia Beyda +4
Planning algorithms are used in computational systems to direct autonomous behavior. In a canonical application, for example, planning for autonomous vehicles is used to automate t…
Measuring and Mitigating the Risk of IP Reuse on Public Clouds
Eric Pauley, Ryan Sheatsley, Blaine Hoak +3
Public clouds provide scalable and cost-efficient computing through resource sharing. However, moving from traditional on-premises service management to clouds introduces new chall…
A Machine Learning and Computer Vision Approach to Geomagnetic Storm Forecasting
Kyle Domico, Ryan Sheatsley, Yohan Beugin +2
Geomagnetic storms, disturbances of Earth's magnetosphere caused by masses of charged particles being emitted from the Sun, are an uncontrollable threat to modern technology. Notab…
Generating Practical Adversarial Network Traffic Flows Using NIDSGAN
Bolor-Erdene Zolbayar, Ryan Sheatsley, Patrick McDaniel +4
Network intrusion detection systems (NIDS) are an essential defense for computer networks and the hosts within them. Machine learning (ML) nowadays predominantly serves as the basi…
Improving Radioactive Material Localization by Leveraging Cyber-Security Model Optimizations
Ryan Sheatsley, Matthew Durbin, Azaree Lintereur +1
One of the principal uses of physical-space sensors in public safety applications is the detection of unsafe conditions (e.g., release of poisonous gases, weapons in airports, tain…
HoneyModels: Machine Learning Honeypots
Ahmed Abdou, Ryan Sheatsley, Yohan Beugin +2
Machine Learning is becoming a pivotal aspect of many systems today, offering newfound performance on classification and prediction tasks, but this rapid integration also comes wit…
Building a Privacy-Preserving Smart Camera System
Yohan Beugin, Quinn Burke, Blaine Hoak +5
Millions of consumers depend on smart camera systems to remotely monitor their homes and businesses. However, the architecture and design of popular commercial systems require user…
On the Robustness of Domain Constraints
Ryan Sheatsley, Blaine Hoak, Eric Pauley +3
Machine learning is vulnerable to adversarial examples-inputs designed to cause models to perform poorly. However, it is unclear if adversarial examples represent realistic inputs…
Adversarial Examples in Constrained Domains
Ryan Sheatsley, Nicolas Papernot, Michael Weisman +2
Machine learning algorithms have been shown to be vulnerable to adversarial manipulation through systematic modification of inputs (e.g., adversarial examples) in domains such as i…
Curie: Policy-based Secure Data Exchange
Z. Berkay Celik, Hidayet Aksu, Abbas Acar +3
Data sharing among partners---users, organizations, companies---is crucial for the advancement of data analytics in many domains. Sharing through secure computation and differentia…
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
Nicolas Papernot, Fartash Faghri, Nicholas Carlini +23
CleverHans is a software library that provides standardized reference implementations of adversarial example construction techniques and adversarial training. The library may be us…