arXiv:2604. 10062v3 Announce Type: replace Abstract: We study reward poisoning attacks in reinforcement learning (RL), where an adversary manipulates rewards within constrained budgets to force the target RL agent to adopt a policy that aligns with the attacker's objectives.
arXiv:2506. 06891v3 Announce Type: replace Abstract: We study the corruption-robustness of in-context reinforcement learning (ICRL), focusing on the Decision-Pretrained Transformer (DPT, Lee et al.
arXiv:2603. 13026v2 Announce Type: replace Abstract: Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents.
arXiv:2605. 07032v2 Announce Type: replace-cross Abstract: The evolution of generative models from next-token predictors to autonomous engines of complex systems necessitates rigorous safety hardening.
arXiv:2606. 09559v1 Announce Type: cross Abstract: Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems such as robotics systems.
arXiv:2503. 01734v3 Announce Type: replace-cross Abstract: Attacks on machine learning models have been extensively studied through stateless optimization.
arXiv:2505. 19532v2 Announce Type: replace Abstract: The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even write) the victim's policy parameters, observations, or rewards.
arXiv:2606. 29867v1 Announce Type: cross Abstract: Deep Reinforcement Learning (DRL) has achieved significant success in robotics and autonomous systems, yet remains vulnerable to adversarial perturbations that can severely degrade performance.
The paper introduces Adversarial Importance Sampling (Advis), a technique that leverages importance sampling over standard training trajectories to estimate and optimize worst‑case returns without extra environment interactions or auxiliary networks, thereby capturing long‑term robustness. It also presents advrl, a modular PyTorch library that consolidates existing robustness methods and adversarial attacks into single‑file implementations for easier prototyping and reproducible evaluation. Finally, the authors highlight that optimal adversarial hyperparameters do not transfer across agents, prompting evaluation against a broader set of attackers (6–14× more configurations) and demonstrate the effectiveness of their approach on continuous control tasks.
arXiv:2606. 00270v1 Announce Type: new Abstract: Shielding is an effective approach to formally guarantee the safety of reinforcement learning agents in Markov decision processes (MDPs).
The paper presents an algorithm that lets a learning agent ask for help from a mentor and transfer knowledge between similar states, enabling safe and effective learning in Markov decision processes with irreversible dynamics and infinite state spaces. It proves that both regret and the number of mentor queries grow sublinearly over time, using a sequence of three reductions to achieve a general result. The work claims to be the first formal proof that an agent can achieve high reward while becoming self‑sufficient in an unknown, unbounded, high‑stakes environment without resets.
arXiv:2606. 04929v1 Announce Type: new Abstract: LLM post-training proceeds through multiple stages, e.
arXiv:2403. 00420v3 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments.