Entity · paper

Adversarial Attacks on Neural Network Policies

paperactiveadversarial-attacks-on-neural-network-policies-7f757f72·1 events·first seen May 20, 2026

Aliases: Adversarial Attacks on Neural Network Policies

Co-occurring entities

adversarial examples Reinforcement Learning OpenAI

More like this (12)

adversarial examples black-box adversarial attacks Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks adversarial training adversarial robustness Beyond Runtime Enforcement: Shield Synthesis as Defensibility Analysis for Adversarial Networks Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity Generative Adversarial Networks Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?

Recent events (1)

4Openai Blog·May 20, 2026·source ↗

Adversarial Attacks on Neural Network Policies

OpenAI published research examining adversarial attacks on neural network-based reinforcement learning policies. The work investigates how small, carefully crafted perturbations to observations can cause trained RL agents to fail catastrophically. This represents an early investigation into the robustness and safety of learned policies under adversarial conditions.

Evaluation and Benchmarking AI Safety Research adversarial examples Adversarial Attacks on Neural Network Policies Reinforcement Learning +1 more