Backend
Security of Deep Reinforcement Learning for Autonomous Driving: A Survey
arXiv cs.RO0 views
arXiv:2212.06123v5 Announce Type: replace-cross Abstract: Reinforcement learning (RL) enables agents to learn optimal behaviors through interaction with their environment and has been increasingly deployed in safety-critical applications, including autonomous driving. Despite its promise, RL is susceptible to attacks designed either to compromise policy learning or to induce erroneous decisions by trained agents. Although the literature on RL security has grown rapidly and several surveys exist, existing categorizations often fall short in guiding the selection of appropriate defenses for specific systems. In this work, we present a comprehensive survey of 86 recent studies on RL security, addressing these limitations by systematically categorizing attacks and defenses according to defined threat models and single- versus multi-agent settings. Furthermore, we examine the relevance and applicability of state-of-the-art attacks and defense mechanisms within the context of autonomous driving, providing insights to inform the design of robust RL systems.
Source:https://arxiv.org/abs/2212.06123PreviousDailyBrick: Language-Guided Synthesis of Brick Assembly InstructionsNextCurvature-aware 3D length estimation of greenhouse cucumbers using RGB-D imaging and cubic spline arc-length integration
Related posts
![UI Practice - Duolingo [1]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2F8uawvr6a0e07ilktpkk7.png)
UI Practice - Duolingo [1]
0dev.to UX
Running Breath of the Wild natively on Windows with a static recompiler
0dev.to GitHub

Microsoft Ignite 2026 Book of News: My Six Picks for DevOps Teams
0dev.to GitHub

Which of your GitHub Actions survive a move to Codeberg
0dev.to GitHub
Most Binance altcoin ideas die at the fee. Five that survived their own cost screen
0dev.to Data
Seven Runs Took the First 100 TikTok Comments. None of Them Had the 185-Like One
0dev.to Data