Search Results for author:
Found 6 papers, 4 papers with code
Perfectly Secure Steganography Using Minimum Entropy Coupling
In this work, we show that a steganography procedure is perfectly secure under \citet{cachin_perfect}'s information theoretic-model of steganography if and only if it is induced by a coupling.
Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS
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.
Communicating via Markov Decision Processes
We contribute a theoretically grounded approach to MCGs based on maximum entropy reinforcement learning and minimum entropy coupling that we call MEME.
SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbations
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.
QPEP: A QUIC-Based Approach to Encrypted Performance Enhancing Proxies for High-Latency Satellite Broadband
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
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.
