Red-Teaming & Adversarial Robustness - Weekly Roundup

MotionForge is introduced, the first large- scale simulation benchmark and data-generation pipeline tailored to jointly evaluate domain shifts and long-horizon interaction in dynamic manipulation, exposing a critical gap between current policy capabilities and the requirements of robust long- horizon manipulation of dynamic objects under domain shifts.

This work proposes RoboMP-DINOv2 (Robotics Mask-Prompted DINOv2), a full-scene vision encoder that treats masks as spatial prompts rather than visibility filters, and introduces masked-region color randomization (MCR) to improve appearance robustness, yielding RoboMP-DINOv2-MCR.

A strong target-specific calibration-transfer error can exist within one frozen environment, but the evidence does not establish that the error is intrinsic to the model or general across benchmarks.

Missing sensory streams typically break audiovisual tracking, but routing audio, face, and mouth inputs through modality-agnostic query attention shatters previous active speaker detection records across five benchmarks by up to 5.1 mAP.

A ROS-integrated framework, built on Isaac Sim, for large-scale procedural generation of agricultural environments, with built-in support for row crops, orchards, and vineyards and straightforward extensibility to additional crop categories is presented.

CDKF-Track is the first framework to jointly address detection-level fusion redundancy and learnable motion modeling in cooperative 3D MOT, and achieves up to 27.99% improvements in tracking accuracy over state-of-the-art multi-agent MOT methods.

IndustrialVLA-Bench is presented, an evidence-aware evaluation of six released VLA and WAM systems under a unified reporting schema that evaluates clean capability on LIBERO, non-language robustness on LIBERO-Plus, instruction sensitivity on LIBERO-Para, and observed execution cost.

A digital twin-driven virtual reality (VR) teleoperation platform, where the digital twin is created from markerless perception of the surgical environment and streamed for display on the HMD, which significantly outperforms a state-of-the-art HoloLens 2 mixed reality baseline.

A teacher-student framework combining an improved visual encoder architecture, persistent feature masking, and a novel consensus-gating algorithm to retain useful depth information under unmodeled corruption, which improves robustness where augmentation coverage is missing.

This work adds one feature-alignment term to ordinary VLA training: a frozen world model is run over the training frames once and cached, and the student learns to agree with that cache, indicating a broad representational prior rather than a fragile alignment between two particular networks.

A strict temporal split is addressed with every model trained on one period and scored once on a later one, which results in results about robustness to distribution shift, not malware evolution.

An exploratory case study that applies explainable artificial intelligence techniques to analyze how Prompt Guard 2 distinguishes malicious from benign prompts finds that Prompt Guard 2's decisions rely on the cumulative contribution of many tokens rather than a few dominant ones, yet saliency-guided synonym substitution and sentence-level paraphrasing can flip its predictions.

This work proposes a novel approach under the more realistic black-box threat model that utilizes concepts from reinforcement learning to optimize perturbations with a non-differentiable target model, and shows the success of reinforcement learning inspired black-box adversarial attack (RIBA) in generating adversarial perturbations using only a small number of queries to the target model.

SBMVTrack is proposed, a fully spiking framework for energy-efficient UAV tracking that introduces Energy-Weighted Spike Budgeting (EWSB), a method that constrains the energy-weighted firing rate and saturation activity, thereby reducing redundant spike computations.

This work presents GINIO, a geometric SO(3)-equivariant interface for neural inertial odometry under arbitrary rotations of the IMU measurement frame, and introduces Last-Frame Alignment (LFA), a deterministic preprocessing step that is provably equivalent to world-frame training for SO(3)-equivariant predictors.

Two geometric regularization strategies (hinged Riesz log-energy and effective-dimension maximization) applied to classifier prototypes to encourage more uniform hyperspherical coverage are investigated and the resulting prototype sets exhibit higher effective dimensionality and improved isotropy.

This work proposes replacing an empty representation with a learnable unconditional embedding, optimized to represent a meaningful unconditional state, and shows that learnable null embeddings consistently outperform fixed null embeddings across speaker similarity, speech stability, and expressiveness, while exhibiting greater robustness to larger guidance scales.

Structuring 4D diffusion acquisitions as geometric q-space graphs slashes slice-to-volume registration error by 73% over standard tools like FSL eddy—completely zero-shot and without ground-truth motion supervision.

A query optimization framework that integrates a Graph Transformer with the model-based reinforcement learning (RL) algorithm MuZero, which converts SQL queries into heterogeneous graphs containing tables, predicates, and join operators and demonstrates its practical effectiveness and scientific value for building high-performance, adaptive intelligent database systems.

This work finds that the wording of the question affects VLMs in two opposite ways: verbose paraphrasing reduces drift variance by 70--81% on the 8B models and the practical recipe---pad the prompt---further yields measurable gains in accuracy, even under image corruption.

MERIT-Rank is proposed, a framework that models complementary reasoning trajectories to improve reranking robustness and develops Progressive Rank Policy Optimization (PRPO), a progressive training framework that stabilizes reasoning trajectories while continually improving ranking quality through staged optimization objectives.

A physics-enhanced machine learning approach for the system identification of Linear Time-Varying systems under time-varying operating conditions in terms of fast-varying natural frequencies and damping ratios by combining a long short-term memory network with an Extended Kalman Filter is proposed.

Delphi Scanner is introduced, a static malware detection system for Windows PE files that balances efficiency with behavioral interpretation that uses a convolutional neural network to model Windows API sequences to classify PE and a decoupled interpretation layer based on a rule-based layer to categorize APIs into high-level malicious capabilities.

Findings indicate that Federated Learning is a safe and efficient solution to AI-assisted diagnosis in contemporary healthcare when combined with the use of sophisticated object detection models.

LLM-Falsifier is shown to outperform existing falsification tools based on a range of optimization paradigms, from surrogate-based and Bayesian optimization to search-based testing, on 14 of 21 specifications when measured by the average number of simulations required to find a counterexample.

This paper proposes ROGUE, a framework that dynamically constructs robust detection workflows by orchestrating multiple detection tools and introduces a dual-agent paradigm, where a perturbation agent generates audio perturbations and a policy agent learns to select and execute detection tools under perturbed conditions.

Governance-as-Code (GaC), a framework of 43 machine-checkable acceptance criteria across six compliance modules that run in a CI/CD pipeline and emit Article-indexed audit evidence, is delivered and the actual Rego policy code is shown, showing the actual Rego policy code rather than merely describing it.

It is demonstrated that gradient-based attribution methods track format similarity more than task semantics, meaning that such methods, as well as the semantic interpretation of the gradient, should be tested on data where answer format and task vary independently for greater robustness and reliability.

FARSIGHT (Financial Agent Robustness and Security Investigation and Global Holistic Testing), a framework that performs scheme-level evaluation of financial LLM agents on two axes: robustness under market turbulence and security against three attack types: attacks on information sources, attacks on agents, and agent-as-attacker behaviors.

Experimental results show that SOLAR consistently outperforms state-of-the-art vision-only, vision-language, and task-specific models across all tasks, demonstrating superior accuracy, robustness, and multimodal reasoning.

The method retains a nominal task-space controller for structured insertion and seating, while residual PPO supplies bounded local corrections and decides when to release and supports a hybrid design in which geometry preserves reliable task structure and learning is concentrated on the contact-sensitive behaviour that fixed rules handle poorly.