Adversarial ML Problems Are Getting Harder to Solve and to Evaluate

J Rando, J Zhang, N Carlini, F Tramèr - arxiv preprint arxiv:2502.02260, 2025 - arxiv.org
In the past decade, considerable research effort has been devoted to securing machine
learning (ML) models that operate in adversarial settings. Yet, progress has been slow even …

Position: Towards a Responsible LLM-empowered Multi-Agent Systems

J Hu, Y Dong, S Ao, Z Li, B Wang, L Singh… - arxiv preprint arxiv …, 2025 - arxiv.org
The rise of Agent AI and Large Language Model-powered Multi-Agent Systems (LLM-MAS)
has underscored the need for responsible and dependable system operation. Tools like …