arXiv:2606. 16605v1 Announce Type: new Abstract: World models are widely used in robotic and agentic engineering control systems due to their ability to learn latent dynamics for planning and decision-making.
SEBA is a sample‑efficient framework for black‑box adversarial attacks on visual reinforcement learning agents. It combines a shadow Q model, a generative adversarial network for imperceptible perturbations, and a world model to simulate dynamics, reducing real‑world queries. Experiments on MuJoCo and Atari show SEBA significantly lowers cumulative rewards while preserving visual fidelity and requiring far fewer environment interactions than previous methods.
arXiv:2607. 11063v1 Announce Type: new Abstract: Despite progress in Embodied AI, Vision-and-Language Navigation systems remain vulnerable to adversarial visual disturbances.
arXiv:2606. 10371v1 Announce Type: cross Abstract: Diffusion-based action generation has become a foundational component of embodied AI, but its reliance on visual conditioning leaves deployed visuomotor policies vulnerable to adversarial manipulation.
arXiv:2605.23220v2 Announce Type: replace Abstract: Despite the growing use of world models as decision-making agents, their adversarial robustness remains underexplored due to the lack of dedicated...
TrojanWorld is a backdoor framework that targets world-model agents by steering their internal imagination toward attacker-specified actions when a physical trigger is present. The attack uses Decision-Reflective Induction, Clean Behavior Anchoring, and Causal Propagation to maintain stealth, persistence, and high performance. Experiments on TD-MPC2, DreamerV3, and R2-Dreamer across several benchmarks show that the attack can induce target actions with minimal performance loss and can keep agents on a malicious trajectory even after the trigger is removed.
MAC‑v2 is a new framework for long‑horizon model‑based value expansion from pixel observations in offline reinforcement learning. It trains a reconstruction‑free latent world model that learns representations through prediction and control objectives, avoiding the need to encode control‑irrelevant visual details. By using action chunking, MAC‑v2 reduces recursive model predictions, mitigating error accumulation and achieving strong performance on visual benchmarks such as OGBench, MMBench2, Robomimic, and LIBERO‑10.
The paper introduces TempJail, a temporal jailbreak framework targeting image‑to‑video generation models. It exploits a newly identified vulnerability where unsafe semantics arise from the composition of frames over time, rather than from single‑frame violations. By decomposing malicious captions into visual conditions and temporal instructions, and by employing controlled latent perturbations and template rewriting, TempJail achieves a 23.3 % higher attack success rate than prior methods on several commercial models.
The paper introduces the Viability‑constrained Behavioral Steering Attack (V‑BSA), a new attack strategy for federated reinforcement learning that targets the timing of interventions rather than just the construction of malicious updates. By selecting sparse intervention states based on local policy uncertainty and applying envelope‑constrained steering, V‑BSA can significantly degrade performance on discrete‑action benchmarks while using far fewer interventions than traditional dense poisoning attacks. The study demonstrates that the specific states at which interventions occur constitute a distinct and critical dimension of robustness in sequential decision‑making settings.
arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that...
arXiv:2602. 01658v2 Announce Type: replace-cross Abstract: Bandit algorithms have recently emerged as a powerful tool for evaluating machine learning models, including generative image models and large language models, by efficiently identifying top-performing candidates without exhaustive comparisons.
The paper introduces Critic-Guided Synthetic Experience (CGSE), a method that uses a frozen latent world model to generate new transitions offline. CGSE samples candidate actions from an offline policy, refines them to maximize a first‑order approximation of the Q‑function within a trust region, and then uses the critic to select the best action for each imagined transition. The resulting synthetic transitions are added to the replay buffer, improving an offline policy’s success rate by 7.1% on three OGBench manipulation tasks.