72 citations · 79 across the 6 of their papers we have counts for
7 papers
Beyond Predictable Paths: Redefining AI Security Incident Reporting for Agents
Anastasia Pustozerova, Eugene Bagdasarian, Luca Beurer-Kellner +22
AI agents are being deployed rapidly, accompanied by a growing number of AI-specific attacks and corresponding incidents. As incident reporting becomes increasingly important for l…
DPM: Clustering Sensitive Data through Separation
Johannes Liebenow, Yara Schütt, Tanya Braun +3
Clustering is an important tool for data exploration where the goal is to subdivide a data set into disjoint clusters that fit well into the underlying data structure. When dealing…
Private Blind Model Averaging - Distributed, Non-interactive, and Convergent
Moritz Kirschte, Sebastian Meiser, Saman Ardalan +1
Distributed differentially private learning techniques enable a large number of users to jointly learn a model without having to first centrally collect the training data. At the s…
Learning Numeric Optimal Differentially Private Truncated Additive Mechanisms
David M. Sommer, Lukas Abfalterer, Sheila Zingg +1
Differentially private (DP) mechanisms face the challenge of providing accurate results while protecting their inputs: the privacy-utility trade-off. A simple but powerful techniqu…
Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions
Eike Petersen, Yannik Potdevin, Esfandiar Mohammadi +8
Machine learning is expected to fuel significant improvements in medical care. To ensure that fundamental principles such as beneficence, respect for human autonomy, prevention of…
Differential privacy with partial knowledge
Damien Desfontaines, Esfandiar Mohammadi, Elisabeth Krahmer +1
Differential privacy offers formal quantitative guarantees for algorithms over datasets, but it assumes attackers that know and can influence all but one record in the database. Th…
Computational Soundness for Dalvik Bytecode
Michael Backes, Robert Künnemann, Esfandiar Mohammadi
Automatically analyzing information flow within Android applications that rely on cryptographic operations with their computational security guarantees imposes formidable challenge…