adversarial AI

3 items

RESEARCHarXiv CS.LG·4/17/2026

Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees

This research addresses the challenge of decision-making in environments with strategic adversaries or external factors, where traditional policies can fail catastrophically in safety-critical settings. It proposes an optimistic policy learning approach designed to account for these interactions and provide regret and violation guarantees.

reinforcement learning robust AI adversarial AI

DOCDEV.to AI·5/3/2026

DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses

DeepRobust is a PyTorch library designed for research and development in adversarial attacks and defenses. It provides tools for testing the robustness of deep learning models against malicious manipulations.

deep learning security machine learning adversarial AI

NEWSDEV.to AI·4/21/2026

BotConduct Training Center: free adversarial evaluation for your AI agent

BotConduct Training Center launched a free tier for adversarial evaluation of AI agents. The platform tests agent robustness against attacks like prompt extraction, authority impersonation, and contradictory information, revealing where they break before production.

security adversarial AI AI testing