1.6k citations
- GSI Helmholtz Centre for Heavy Ion ResearchDE1k papers
- Centre National de la Recherche ScientifiqueFR363 papers
- ExtreMe Matter Institute EMMIDE361 papers
- Heidelberg UniversityDE283 papers
- Goethe University FrankfurtDE260 papers
- Michigan State UniversityUS258 papers
- Joint Institute for Nuclear ResearchRU238 papers
- Max Planck Institute for Nuclear PhysicsDE227 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR222 papers
- European Organization for Nuclear ResearchCH212 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR211 papers
- Lawrence Berkeley National LaboratoryUS211 papers
112 papers · 1 filter
Unlocking Apple's Private Cloud Compute: An Analysis of Privacy-Preserving Artificial Intelligence
Yannik Dittmar, Marvin Jerome Stephan, Thomas Völkl +2
Many existing Artificial Intelligence (AI) solutions on mobile devices rely on an extensive collection of sensitive data, raising privacy concerns and often requiring storage for b…
WOOTdroid: Whole-system Online On-device Tracing for Android
Simon Althaus, Nikolaos Alexopoulos, Max Mühlhäuser +2
System auditing on Android faces two problems. First, existing syscall tracers lose events under load, silently overwriting entries faster than a user space reader can drain them.…
ARIstoteles -- Dissecting Apple's Baseband Interface
Tobias Kröll, Stephan Kleber, Frank Kargl +2
Wireless chips and interfaces expose a substantial remote attack surface. As of today, most cellular baseband security research is performed on the Android ecosystem, leaving a hug…
NeuroStrike: Neuron-Level Attacks on Aligned LLMs
Lichao Wu, Sasha Behrouzi, Mohamadreza Rostami +3
Safety alignment is critical for the ethical deployment of large language models (LLMs), guiding them to avoid generating harmful or unethical content. Current alignment techniques…
SkyEye: When Your Vision Reaches Beyond IAM Boundary Scope in AWS Cloud
Minh Hoang Nguyen, Anh Minh Ho, Bao Son To
In recent years, cloud security has emerged as a primary concern for enterprises due to the increasing trend of migrating internal infrastructure and applications to cloud environm…
SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)
Phillip Rieger, Alessandro Pegoraro, Kavita Kumari +3
Split Learning (SL) is a distributed deep learning approach enabling multiple clients and a server to collaboratively train and infer on a shared deep neural network (DNN) without…