research
∙
08/18/2023
Attesting Distributional Properties of Training Data for Machine Learning
The success of machine learning (ML) has been accompanied by increased c...
share
research
∙
08/12/2023
Copilot Security: A User Study
Code generation tools driven by artificial intelligence have recently be...
research
∙
07/27/2023
FLARE: Fingerprinting Deep Reinforcement Learning Agents using Universal Adversarial Masks
We propose FLARE, the first fingerprinting mechanism to verify whether a...
research
∙
06/08/2023
Parallel and Asynchronous Smart Contract Execution
Today's blockchains suffer from low throughput and high latency, which i...
research
∙
04/17/2023
GrOVe: Ownership Verification of Graph Neural Networks using Embeddings
Graph neural networks (GNNs) have emerged as a state-of-the-art approach...
research
∙
10/20/2022
Towards cryptographically-authenticated in-memory data structures
Modern processors include high-performance cryptographic functionalities...
research
∙
07/05/2022
Conflicting Interactions Among Protections Mechanisms for Machine Learning Models
Nowadays, systems based on machine learning (ML) are widely used in diff...
research
∙
04/20/2022
BliMe: Verifiably Secure Outsourced Computation with Hardware-Enforced Taint Tracking
We present Blinded Memory (BliMe), a way to realize efficient and secure...
research
∙
04/10/2022
Is GitHub's Copilot as Bad As Humans at Introducing Vulnerabilities in Code?
Several advances in deep learning have been successfully applied to the ...
research
∙
04/08/2022
Color My World: Deterministic Tagging for Memory Safety
Hardware-assisted memory protection features are increasingly being depl...
research
∙
02/25/2022
On the Effectiveness of Dataset Watermarking in Adversarial Settings
In a data-driven world, datasets constitute a significant economic value...
research
∙
02/19/2022
Do Transformers use variable binding?
Increasing the explainability of deep neural networks (DNNs) requires ev...
research
∙
12/04/2021
SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning
Data used to train machine learning (ML) models can be sensitive. Member...
research
∙
06/16/2021
Real-time Attacks Against Deep Reinforcement Learning Policies
Recent work has discovered that deep reinforcement learning (DRL) polici...
research
∙
04/26/2021
Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Generative Adversarial Networks
Machine learning models are typically made available to potential client...
research
∙
09/25/2020
A little goes a long way: Improving toxic language classification despite data scarcity
Detection of some types of toxic language is hampered by extreme scarcit...
research
∙
08/17/2020
WAFFLE: Watermarking in Federated Learning
Creators of machine learning models can use watermarking as a technique ...
research
∙
10/11/2019
Extraction of Complex DNN Models: Real Threat or Boogeyman?
Recently, machine learning (ML) has introduced advanced solutions to man...
research
∙
09/12/2019
Protecting the stack with PACed canaries
Stack canaries remain a widely deployed defense against memory corruptio...
research
∙
06/08/2019
Making targeted black-box evasion attacks effective and efficient
We investigate how an adversary can optimally use its query budget for t...
research
∙
06/03/2019
DAWN: Dynamic Adversarial Watermarking of Neural Networks
Training machine learning (ML) models is expensive in terms of computati...
research
∙
05/31/2019
Effective writing style imitation via combinatorial paraphrasing
Stylometry can be used to profile authors based on their written text. T...
research
∙
05/24/2019
Making Speculative BFT Resilient with Trusted Monotonic Counters
Consensus mechanisms used by popular distributed ledgers are highly scal...
research
∙
05/24/2019
PACStack: an Authenticated Call Stack
A popular run-time attack technique is to compromise the control-flow in...
research
∙
02/25/2019
EAT2seq: A generic framework for controlled sentence transformation without task-specific training
We present EAT2seq: a novel method to architect automatic linguistic tra...
research
∙
02/25/2019
Using logical form encodings for unsupervised linguistic transformation: Theory and applications
We present a novel method to architect automatic linguistic transformati...
research
∙
02/24/2019
Text Analysis in Adversarial Settings: Does Deception Leave a Stylistic Trace?
Textual deception constitutes a major problem for online security. Many ...
research
∙
02/22/2019
Exploitation Techniques and Defenses for Data-Oriented Attacks
Data-oriented attacks manipulate non-control data to alter a program's b...
research
∙
11/22/2018
PAC it up: Towards Pointer Integrity using ARM Pointer Authentication
Run-time attacks against programs written in memory-unsafe programming l...
research
∙
10/14/2018
S-FaaS: Trustworthy and Accountable Function-as-a-Service using Intel SGX
Function-as-a-Service (FaaS) is a recent and already very popular paradi...
research
∙
08/28/2018
All You Need is "Love": Evading Hate-speech Detection
With the spread of social networks and their unfortunate use for hate sp...
research
∙
07/13/2018
ASSURED: Architecture for Secure Software Update of Realistic Embedded Devices
Secure firmware update is an important stage in the IoT device life-cycl...
research
∙
05/07/2018
PRADA: Protecting against DNN Model Stealing Attacks
As machine learning (ML) applications become increasingly prevalent, pro...
research
∙
05/07/2018
Stay On-Topic: Generating Context-specific Fake Restaurant Reviews
Automatically generated fake restaurant reviews are a threat to online r...
research
∙
04/23/2018
Keys in the Clouds: Auditable Multi-device Access to Cryptographic Credentials
Personal cryptographic keys are the foundation of many secure services, ...
research
∙
04/20/2018
DIoT: A Self-learning System for Detecting Compromised IoT Devices
IoT devices are being widely deployed. Many of them are vulnerable due t...
research
∙
04/20/2018
DÏoT: A Crowdsourced Self-learning Approach for Detecting Compromised IoT Devices
IoT devices are being widely deployed. Many of them are vulnerable due t...
research
∙
03/29/2018
Migrating SGX Enclaves with Persistent State
Hardware-supported security mechanisms like Intel Software Guard Extensi...
research
∙
03/20/2018
Proximity Verification Based on Acoustic Room Impulse Response
Device proximity verification has a wide range of security applications ...
research
∙
10/17/2017
Towards Linux Kernel Memory Safety
The security of billions of devices worldwide depends on the security an...
research
∙
07/16/2014