research
∙
07/17/2023
Secure Composition of Robust and Optimising Compilers
To ensure that secure applications do not leak their secrets, they are r...
share
research
∙
11/17/2022
Towards Good Practices in Evaluating Transfer Adversarial Attacks
Transfer adversarial attacks raise critical security concerns in real-wo...
research
∙
10/17/2022
A Systematic Study of the Consistency of Two-Factor Authentication User Journeys on Top-Ranked Websites (Extended Version)
Heuristics for user experience state that users will transfer their expe...
research
∙
09/07/2022
Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots
Chatbots are used in many applications, e.g., automated agents, smart ho...
research
∙
11/22/2021
Bilingual Problems: Studying the Security Risks Incurred by Native Extensions in Scripting Languages
Scripting languages are continuously gaining popularity due to their eas...
research
∙
10/11/2021
Towards a Principled Approach for Dynamic Analysis of Android's Middleware
The Android middleware, in particular the so-called systemserver, is a c...
research
∙
10/06/2021
Inference Attacks Against Graph Neural Networks
Graph is an important data representation ubiquitously existing in the r...
research
∙
05/08/2021
Mental Models of Adversarial Machine Learning
Although machine learning (ML) is widely used in practice, little is kno...
research
∙
03/27/2021
Graph Unlearning
The right to be forgotten states that a data subject has the right to er...
research
∙
02/10/2021
Node-Level Membership Inference Attacks Against Graph Neural Networks
Many real-world data comes in the form of graphs, such as social network...
research
∙
02/04/2021
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
Inference attacks against Machine Learning (ML) models allow adversaries...
research
∙
12/30/2020
PrivSyn: Differentially Private Data Synthesis
In differential privacy (DP), a challenging problem is to generate synth...
research
∙
10/07/2020
Don't Trigger Me! A Triggerless Backdoor Attack Against Deep Neural Networks
Backdoor attack against deep neural networks is currently being profound...
research
∙
10/06/2020
BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models
The tremendous progress of autoencoders and generative adversarial netwo...
research
∙
09/10/2020
Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning
While being deployed in many critical applications as core components, m...
research
∙
07/14/2020
Adversarial Examples and Metrics
Adversarial examples are a type of attack on machine learning (ML) syste...
research
∙
06/12/2020
How many winning tickets are there in one DNN?
The recent lottery ticket hypothesis proposes that there is one sub-netw...
research
∙
06/11/2020
A new measure for overfitting and its implications for backdooring of deep learning
Overfitting describes the phenomenon that a machine learning model fits ...
research
∙
06/01/2020
BadNL: Backdoor Attacks Against NLP Models
Machine learning (ML) has progressed rapidly during the past decade and ...
research
∙
06/01/2020
Adversarial Attacks on Classifiers for Eye-based User Modelling
An ever-growing body of work has demonstrated the rich information conte...
research
∙
05/25/2020
Decentralized Privacy-Preserving Proximity Tracing
This document describes and analyzes a system for secure and privacy-pre...
research
∙
05/05/2020
When Machine Unlearning Jeopardizes Privacy
The right to be forgotten states that a data owner has the right to eras...
research
∙
05/05/2020
Stealing Links from Graph Neural Networks
Graph data, such as social networks and chemical networks, contains a we...
research
∙
04/19/2020
Trollthrottle – Raising the Cost of Astroturfing
Astroturfing, i.e., the fabrication of public discourse by private or st...
research
∙
03/07/2020
Dynamic Backdoor Attacks Against Machine Learning Models
Machine learning (ML) has made tremendous progress during the past decad...
research
∙
10/31/2019
Causality Control Flow
Causality has been the issue of philosophic debate since Hippocrates. It...
research
∙
09/23/2019
MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples
In a membership inference attack, an attacker aims to infer whether a da...
research
∙
09/19/2019
Adversarial Vulnerability Bounds for Gaussian Process Classification
Machine learning (ML) classification is increasingly used in safety-crit...
research
∙
09/09/2019
Proconda – Protected Control Data
Memory corruption vulnerabilities often enable attackers to take control...
research
∙
04/01/2019
Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning
Machine learning (ML) has progressed rapidly during the past decade and ...
research
∙
02/08/2019
Adversarial Initialization -- when your network performs the way I want
The increase in computational power and available data has fueled a wide...
research
∙
12/06/2018
The Limitations of Model Uncertainty in Adversarial Settings
Machine learning models are vulnerable to adversarial examples: minor pe...
research
∙
09/13/2018
Fidelius: Protecting User Secrets from Compromised Browsers
Users regularly enter sensitive data, such as passwords, credit card num...
research
∙
08/01/2018
MLCapsule: Guarded Offline Deployment of Machine Learning as a Service
With the widespread use of machine learning (ML) techniques, ML as a ser...
research
∙
06/06/2018
Killing Three Birds with one Gaussian Process: Analyzing Attack Vectors on Classification
The wide usage of Machine Learning (ML) has lead to research on the atta...
research
∙
06/04/2018
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
Machine learning (ML) has become a core component of many real-world app...
research
∙
05/28/2018
Automated Verification of Accountability in Security Protocols
Accounting for misbehavior, instead of postulating trustworthiness, has ...
research
∙
02/12/2018
Tagvisor: A Privacy Advisor for Sharing Hashtags
Hashtag has emerged as a widely used concept of popular culture and camp...
research
∙
12/24/2017
Studying the Impact of Managers on Password Strength and Reuse
Despite their well-known security problems, passwords are still the incu...
research
∙
11/17/2017
How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models
Machine learning models are vulnerable to adversarial examples: minor, i...
research
∙
11/15/2017
CTRL+Z: Recovering Anonymized Social Graphs
Social graphs derived from online social interactions contain a wealth o...
research
∙
05/15/2017
Simulated Penetration Testing and Mitigation Analysis
Penetration testing is a well-established practical concept for the iden...
research
∙
02/21/2017
On the (Statistical) Detection of Adversarial Examples
Machine Learning (ML) models are applied in a variety of tasks such as n...
research
∙
06/14/2016