Competing objectives arise when a model's capabilities

We also define the clean reversed conditional transition as Eq. Thus, a( t) and b (t) can be derived as Eq. The KL-divergence loss of the reversed transition can be simplified as Eq. Thus, we can finally write down the clean loss function Eq. (9) with reparametrization This section will further extend the derivation of the clean diffusion models in Appendix B.1 and Recall the definition of the backdoor reversed conditional transition in Eq. (10). We mark the coefficients of the r as red.

Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising.

As AI systems migrate to safety-critical domains, verifying that their actions comply with well-defined rules remains a challenge. Formal methods provide provable guarantees but demand hand-crafted temporal-logic specifications, offering limited expressiveness and accessibility. Deep learning approaches enable evaluation of plans against natural-language constraints, yet their opaque decision process invites misclassifications with potentially severe consequences. We introduce RepV, a neurosymbolic verifier that unifies both views by learning a latent space where safe and unsafe plans are linearly separable. Starting from a modest seed set of plans labeled by an off-the-shelf model checker, RepV trains a lightweight projector that embeds each plan, together with a language model-generated rationale, into a low-dimensional space; a frozen linear boundary then verifies compliance for unseen natural-language rules in a single forward pass. Beyond binary classification, RepV provides a probabilistic guarantee on the likelihood of correct verification based on its position in the latent space. This guarantee enables a guarantee-driven refinement of the planner, improving rule compliance without human annotations. Empirical evaluations show that RepV improves compliance prediction accuracy by up to 15% compared to baseline methods while adding fewer than 0.2M parameters. Furthermore, our refinement framework outperforms ordinary fine-tuning baselines across various planning domains. These results show that safety-separable latent spaces offer a scalable, plug-and-play primitive for reliable neurosymbolic plan verification. Code and data are available at: https://repv-project.github.io/.

Competing objectives arise when a model's capabilities

As 3D Gaussian Splatting (3DGS) gains rapid adoption in safety-critical tasks for efficient novel-view synthesis from static images, how might an adversary tamper images to cause harm? We introduce ComplicitSplat, the first attack that exploits standard 3DGS shading methods to create viewpoint-specific camouflage - colors and textures that change with viewing angle - to embed adversarial content in scene objects that are visible only from specific viewpoints and without requiring access to model architecture or weights. Our extensive experiments show that ComplicitSplat generalizes to successfully attack a variety of popular detector - both single-stage, multi-stage, and transformer-based models on both real-world capture of physical objects and synthetic scenes. To our knowledge, this is the first black-box attack on downstream object detectors using 3DGS, exposing a novel safety risk for applications like autonomous navigation and other mission-critical robotic systems.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. FBI investigators identified Robert Jacob Hoopes as a suspect in the injury of an ICE officer during protests in Portland, Ore., using facial recognition software, according to a criminal complaint from the case. In the criminal complaint, an unidentified FBI special agent said that a photo shared on OregonLive.com -- the online version of The Oregonian -- was put into "commercially available facial recognition software." The software allegedly provided 30 possible comparison photos from public databases. FBI Portland reviewed the photos and found one from a Reed College SmugMug page called "Canyon Day April '23," in which a tattoo on the suspect's forearm is visible.

Sign up for the Slatest to get the most insightful analysis, criticism, and advice out there, delivered to your inbox daily. Earlier this year, I tried to convince my mother-in-law to ride in one of Waymo's driverless taxis in San Francisco. It was a tough sell at first, but was helped along by a series of careening Uber rides, which prompted the question: How much worse could a robot drive? The answer, at least for us, as our Waymo carried us gently down the city's famous hills from stop sign to stop sign, was clear. We felt safer with no one behind the wheel.