Search Results for author: Martin Strohmeier

Found 8 papers, 5 papers with code

Secret Collusion Among Generative AI Agents

no code implementations12 Feb 2024 Sumeet Ramesh Motwani, Mikhail Baranchuk, Martin Strohmeier, Vijay Bolina, Philip H. S. Torr, Lewis Hammond, Christian Schroeder de Witt

In this paper, we comprehensively formalise the problem of secret collusion in systems of generative AI agents by drawing on relevant concepts from both the AI and security literature.

Perfectly Secure Steganography Using Minimum Entropy Coupling

1 code implementation24 Oct 2022 Christian Schroeder de Witt, Samuel Sokota, J. Zico Kolter, Jakob Foerster, Martin Strohmeier

Steganography is the practice of encoding secret information into innocuous content in such a manner that an adversarial third party would not realize that there is hidden meaning.

Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS

no code implementations23 Nov 2021 Christian Schroeder de Witt, Yongchao Huang, Philip H. S. Torr, Martin Strohmeier

We then argue that attacker-defender fixed points are themselves general-sum games with complex phase transitions, and introduce a temporally extended multi-agent reinforcement learning framework in which the resultant dynamics can be studied.

Continual Learning Multi-agent Reinforcement Learning +2

Communicating via Markov Decision Processes

1 code implementation17 Jul 2021 Samuel Sokota, Christian Schroeder de Witt, Maximilian Igl, Luisa Zintgraf, Philip Torr, Martin Strohmeier, J. Zico Kolter, Shimon Whiteson, Jakob Foerster

We contribute a theoretically grounded approach to MCGs based on maximum entropy reinforcement learning and minimum entropy coupling that we call MEME.

Multi-agent Reinforcement Learning

SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbations

1 code implementation8 Jul 2020 Giulio Lovisotto, Henry Turner, Ivo Sluganovic, Martin Strohmeier, Ivan Martinovic

Research into adversarial examples (AE) has developed rapidly, yet static adversarial patches are still the main technique for conducting attacks in the real world, despite being obvious, semi-permanent and unmodifiable once deployed.

Object Detection Traffic Sign Recognition

QPEP: A QUIC-Based Approach to Encrypted Performance Enhancing Proxies for High-Latency Satellite Broadband

2 code implementations12 Feb 2020 James Pavur, Martin Strohmeier, Vincent Lenders, Ivan Martinovic

However, status-quo services are often unencrypted by default and vulnerable to eavesdropping attacks.

Cryptography and Security Networking and Internet Architecture Performance

Classi-Fly: Inferring Aircraft Categories from Open Data using Machine Learning

no code implementations30 Jul 2019 Martin Strohmeier, Matthew Smith, Vincent Lenders, Ivan Martinovic

Classi-Fly obtains the correct aircraft category with an accuracy of over 88%, demonstrating that it can improve the meta data necessary for applications working with air traffic communication.

BIG-bench Machine Learning Stock Market Prediction +1

Cannot find the paper you are looking for? You can Submit a new open access paper.