NeurIPS 2023 Workshop MASEC Submissions

A Perfect Collusion Benchmark: How can AI agents be prevented from colluding with information-theoretic undetectability?
Sumeet Ramesh Motwani, Mikhail Baranchuk, Lewis Hammond, Christian Schroeder de Witt
- Published: 31 Oct 2023, Last Modified: 29 Nov 2023
- MASEC@NeurIPS'23 WiPP
- Readers: Everyone
Multiagent Simulators for Social Networks
Aditya Surve, Archit Rathod, Mokshit Surana, Gautam Malpani, Aneesh Shamraj, Sainath Reddy Sankepally, Raghav Jain, Swapneel S Mehta
- Published: 31 Oct 2023, Last Modified: 31 Oct 2023
- MASEC@NeurIPS'23 Poster
- Readers: Everyone
Second-order Jailbreaks: Generative Agents Successfully Manipulate Through an Intermediary
Mikhail Terekhov, Romain Graux, Eduardo Neville, Denis Rosset, Gabin Kolly
- Published: 31 Oct 2023, Last Modified: 29 Nov 2023
- MASEC@NeurIPS'23 Poster
- Readers: Everyone
Assessing Risks of Using Autonomous Language Models in Military and Diplomatic Planning
Gabriel Mukobi, Ann-Katrin Reuel, Juan-Pablo Rivera, Chandler Smith
- Published: 31 Oct 2023, Last Modified: 01 Dec 2023
- MASEC@NeurIPS'23 WiPP
- Readers: Everyone
Dynamics Model Based Adversarial Training For Competitive Reinforcement Learning
Xuan Chen, Guanhong Tao, Xiangyu Zhang
- Published: 31 Oct 2023, Last Modified: 25 Nov 2023
- MASEC@NeurIPS'23 Poster
- Readers: Everyone
Leading the Pack: N-player Opponent Shaping
Alexandra Souly, Timon Willi, Akbir Khan, Robert Kirk, Chris Lu, Edward Grefenstette, Tim Rocktäschel
- Published: 31 Oct 2023, Last Modified: 03 Dec 2023
- MASEC@NeurIPS'23 Oral
- Readers: Everyone
Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learning
Matthias Gerstgrasser, David C. Parkes
- Published: 31 Oct 2023, Last Modified: 03 Nov 2023
- MASEC@NeurIPS'23 Oral
- Readers: Everyone
Cooperative AI via Decentralized Commitment Devices
Xinyuan Sun, Davide Crapis, Matt Stephenson, Jonathan Passerat-Palmbach
- Published: 31 Oct 2023, Last Modified: 31 Oct 2023
- MASEC@NeurIPS'23 Oral
- Readers: Everyone
Generation of Games for Opponent Model Differentiation
David Milec, Viliam Lisý, Christopher Kiekintveld
- Published: 31 Oct 2023, Last Modified: 24 Nov 2023
- MASEC@NeurIPS'23 Poster
- Readers: Everyone
Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning
Aakriti Agrawal, Rohith Aralikatti, Yanchao Sun, Furong Huang
- Published: 31 Oct 2023, Last Modified: 01 Dec 2023
- MASEC@NeurIPS'23 Poster
- Readers: Everyone
Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
Xiangyu Liu, Chenghao Deng, Yanchao Sun, Yongyuan Liang, Furong Huang
- Published: 31 Oct 2023, Last Modified: 31 Oct 2023
- MASEC@NeurIPS'23 WiPP
- Readers: Everyone
I See You! Robust Measurement of Adversarial Behavior
Lars Ankile, Matheus X.V. Ferreira, David Parkes
- Published: 31 Oct 2023, Last Modified: 08 Dec 2023
- MASEC@NeurIPS'23 Oral
- Readers: Everyone
Language Agents as Hackers: Evaluating Cybersecurity Skills with Capture the Flag
John Yang, Akshara Prabhakar, Shunyu Yao, Kexin Pei, Karthik R Narasimhan
- Published: 31 Oct 2023, Last Modified: 14 Nov 2023
- MASEC@NeurIPS'23 Oral
- Readers: Everyone
Defining and Mitigating Collusion in Multi-Agent Systems
Jack Foxabbott, Sam Deverett, Kaspar Senft, Samuel Dower, Lewis Hammond
- Published: 31 Oct 2023, Last Modified: 29 Nov 2023
- MASEC@NeurIPS'23 WiPP
- Readers: Everyone
Decentralized agent-based modeling
Ayush Chopra, Arnau Quera-Bofarull, Nurullah Giray Kuru, Ramesh Raskar
- Published: 31 Oct 2023, Last Modified: 31 Oct 2023
- MASEC@NeurIPS'23 WiPP
- Readers: Everyone
RAVE: Enabling safety verification for realistic deep reinforcement learning systems
Wenbo Guo, Taesung Lee, Kevin Eykholt, Jiyong Jiang
- Published: 31 Oct 2023, Last Modified: 15 Nov 2023
- MASEC@NeurIPS'23 WiPP
- Readers: Everyone
Safe Equilibrium
Sam Ganzfried
- Published: 31 Oct 2023, Last Modified: 31 Oct 2023
- MASEC@NeurIPS'23 Poster
- Readers: Everyone
Robust Q-Learning against State Perturbations: a Belief-Enriched Pessimistic Approach
Xiaolin Sun, Zizhan Zheng
- Published: 31 Oct 2023, Last Modified: 31 Oct 2023
- MASEC@NeurIPS'23 Poster
- Readers: Everyone
Harnessing the Power of Federated Learning in Federated Contextual Bandits
Chengshuai Shi, Kun Yang, Ruida Zhou, Cong Shen
- Published: 31 Oct 2023, Last Modified: 25 Nov 2023
- MASEC@NeurIPS'23 Poster
- Readers: Everyone
Stackelberg Games with Side Information
Keegan Harris, Steven Wu, Maria Florina Balcan
- Published: 31 Oct 2023, Last Modified: 31 Oct 2023
- MASEC@NeurIPS'23 Poster
- Readers: Everyone