The paper introduces OmniVerifier-M1, a multimodal meta-verifier that uses symbolic outputs and decoupled reinforcement learning to provide robust, fine-grained verification and error localization for…

The paper introduces TRON, an online, rule-verifiable environment substrate that generates an unbounded stream of fresh, controllable visual reasoning training instances, significantly improving RL pe…

The paper proposes VERITAS, a framework for improving robot policies through inference-time policy steering and self-improvement using a generator-verifier system.

This paper introduces LLM-as-a-Verifier, a framework for fine-grained verification of LLMs using continuous scores, achieving state-of-the-art performance on various benchmarks.

The paper introduces the Universal Verifier, a robust system for verifying computer use agent (CUA) trajectories, which significantly improves reliability and agreement with human judgment compared to…

GAFSV-Net introduces a novel 2D vision framework by encoding temporal signature data into a six-channel Gramian Angular Field image, significantly improving online signature verification accuracy over…

The paper introduces FraudBench, a multimodal benchmark designed to detect AI-generated fraudulent refund evidence, finding that current AI models struggle significantly with claim-conditioned fake-da…

The paper evaluates the adversarial robustness of two open-source Vision-Language Models (LLaVA and Qwen2.5-VL) in a simulated e-commerce environment, finding that while LLaVA is vulnerable to gradien…

The paper demonstrates that adversarial examples can be used to manipulate Vision-Language Models (VLMs) into confidently providing authoritative but incorrect information, a process termed 'AI author…

This paper introduces InvWeaver, a neuro-symbolic framework for synthesizing loop invariants in programs with multiple interacting loops.

This paper introduces a dual-layer side-channel attack framework that exploits the variable workload introduced by dynamic image preprocessing in local Vision-Language Models (VLMs) to infer sensitive…

This paper proposes a domain-generalized training framework for pixel-level image tampering detection in modern vision-language models, improving robustness and out-of-distribution performance.

This paper proposes using color statistics, specifically through novel color transformations, to detect AI-generated synthetic images by exploiting the color-imitation weaknesses of current generative…

The paper proposes MMGuard, a proactive defense mechanism that injects unlearnable, human-imperceptible perturbations into multimodal data to prevent unauthorized fine-tuning of Large Vision-Language…

The paper proposes a novel, customizable 'Pick and Sort' graphical authentication scheme where users select and arrange visual elements in a grid, demonstrating its feasibility for non-time-critical a…

The paper introduces $ ext{RLR}^3$, a novel framework that extends verifiable rewards in Reinforcement Learning to handle partially verifiable, multi-criteria vision-language tasks by integrating robu…

The paper proposes Cert-LAS, a novel certified method for verifying model ownership in text-to-image diffusion models, which is robust against malicious signal removal attacks.

The paper systematically measures the risk of current image-to-3D models generating harmful geometries, finding that these models are effective at reconstruction and existing safeguards are insufficie…

This paper introduces a Certified Training approach for training provably robust vision models against motion blur perturbations, outperforming Adversarial Training.