Where’s the Liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content

The recent proliferation of photorealistic images created by generative models has sparked both excitement and concern, as these images are increasingly indistinguishable from real ones to the human eye. While offering new creative and commercial possibilities, the potential for misuse, such as in misinformation and fraud, highlights the need for effective detection methods. Current detection approaches often rely on access to model weights or require extensive collections of real image datasets, limiting their scalability and practical application in real-world scenarios. In this work, we introduce a novel black-box detection framework that requires only API access, sidestepping the need for model weights or large auxiliary datasets. Our approach leverages a corrupt-and-recover strategy: by masking part of an image and assessing the model’s ability to reconstruct it, we measure the likelihood that the image was generated by the model itself. For black-box models that do not support masked-image inputs, we incorporate a cost-efficient surrogate model trained to align with the target model’s distribution, enhancing detection capability. Our framework demonstrates strong performance, outperforming baseline methods by 4.31% in mean average precision across eight diffusion model variant datasets.

SimCache: Similarity Caching for Efficient VLM-based Scene Understanding

Scene understanding systems analyze visual contexts by detecting objects, their attributes, and the interactions among them to provide a holistic interpretation. Understanding a scene requires analyzing multiple salient regions within a single video frame. Recently, Vision-Language Models (VLMs) have emerged as powerful tools for scene understanding, leveraging learned world knowledge to enable deployment without specialized training or fine-tuning. However, deploying VLMs in real-time applications is challenging due to their high computational and memory requirements, which limit processing throughput. We propose SimCache, a novel software-based caching mechanism that optimizes VLM-based scene understanding systems by reducing redundant computations. SimCache stores the embedding representation of a salient region and its detected activity, enabling reuse of VLM computations for similar regions in future frames. Specifically, SimCache exploits two types of redundancy: (1) temporal locality, reusing computations for similar regions across adjacent frames, and (2) semantic locality, reusing computations for visually distinct regions that represent the same activity at different times. SimCache includes a multi-tier cache architecture with specialized cache search and refinement policies to exploit redundancy efficiently and accurately. Experiments on action recognition datasets demonstrate that SimCache improves system throughput by up to 9.4× and reduces VLM computations by up to 24.4× with minimal accuracy loss.

Solving Inverse Problems via a Score-Based Prior: An Approximation-Free Posterior Sampling Approach

Diffusion models (DMs) have proven to be effective in modeling high-dimensional distributions, leading to their widespread adoption for representing complex priors in Bayesian inverse problems (BIPs). However, current DM-based posterior sampling methods proposed for solving common BIPs rely on heuristic approximations to the generative process. To exploit the generative capability of DMs and avoid the usage of such approximations, we propose an ensemble-based algorithm that performs posterior sampling without the use of heuristic approximations. Our algorithm is motivated by existing works that combine DM-based methods with the sequential Monte Carlo (SMC) method. By examining how the prior evolves through the diffusion process encoded by the pre-trained score function, we derive a modified partial differential equation (PDE) governing the evolution of the corresponding posterior distribution. This PDE includes a modified diffusion term and a reweighting term, which can be simulated via stochastic weighted particle methods. Theoretically, we prove that the error between the true posterior distribution canbe bounded in terms of the training error of the pre-trained score function and the ]number of particles in the ensemble. Empirically, we validate our algorithm on several inverse problems in imaging to show that our method gives more accurate reconstructions compared to existing DM-based methods.

GFF-Agnostic Black Box Gain Model for non-Flat Input Spectrum

We present a simple and accurate semi-analytical model predicting the gain of a single-stage erbium-doped fiber amplifier (EDFA) embedded with an unknown gain flattening filter (GFF). Characteristic wavelength-dependent gain coefficients and their scaling laws are extracted with a limited set of simple flat input spectrum measurements at variable temperatures and pump powers. Based on a black box approach, the proposed model provides a precise gain profile estimation of GFF-embedded EDFA for non-flat input spectra in variable temperature and pump power conditions. The accuracy of the presented methodology is validated on an extensive experimental dataset and compared with state-of-the-art gain models based on semi-analytic and solutions.

Phase-noise Tolerant Per-span Phase and Polarization Sensing

Subsea cables include a supervisory system that monitors the health of the amplifier pumps and fiber loss on per span basis. In some of the cables, the monitoring is achieved optically and passively using high-loss loop back paths and wavelength selective reflectors. By sending monitoring pulses through the supervisory channel and comparing the phases and polarizations of the returning pulses reflected by consecutive reflectors, dynamic disturbances affecting individual spans can be monitored on a per span basis. Such per-span phase monitoring techniques require high phase coherence compared to DAS systems since the spans are 10s of kms long compared to typical DAS resolution of meters. A time-frequency spread technique was demonstrated to limit the coherence length requirement, however the limits of its effectiveness was not quantified. In this paper we present a detailed analysis of the trade-off between implementation complexity and the phase noise tolerance for given span length by lab experiments.

Efficient Semantic Communication Through Transformer-Aided Compression

Transformers, known for their attention mechanisms, have proven highly effective in focusing on critical elements within complex data. This feature can effectively be used to address the time-varying channels in wireless communication systems. In this work, we introduce a channel-aware adaptive framework for semantic communication, where different regions of the image are encoded and compressed based on their semantic content. By employing vision transformers, we interpret the attention mask as a measure of the semantic contents of the patches and dynamically categorize the patches to be compressed at various rates as a function of the instantaneous channel bandwidth. Our method enhances communication efficiency by adapting the encoding resolution to the content’s relevance, ensuring that even in highly constrained environments, critical information is preserved. We evaluate the proposed adaptive transmission framework using the TinyImageNet dataset, measuring both reconstruction quality and accuracy. The results demonstrate that our approach maintains high semantic fidelity while optimizing bandwidth, providing an effective solution for transmitting multiresolution data in limited bandwidth conditions.

Optical Flow Processing for Chirp-Pulse Coherent OTDR

We propose a novel optical flow processing technique for distributed temperature and strain sensing with the chirped-pulse coherent OTDR. Unlike conventional 1-dimensional cross-correlation methods, the technique treats the 2-dimensional waterfall data as sequential video frames, estimating local shifts through optical flow. The weighted least square approach with adaptive window size enables pixel-level optical flow calculation, providing accurate local shifts via accumulative tracks with enhanced spatial resolution. Preliminary experimental results over 20km fiber demonstrate its effectiveness for dynamic temperature and strain sensing, addressing limitations of traditional methods and improving sensing capabilities.

Detection of Waves and Sea-Surface Vessels via Time Domain Only Analysis of Underwater DAS Data

A 100-meter-long fiber optic cable was installed at the bottom of a water tank at the Davidson Laboratory, together with a hydrophone for reference. The water tank is approximately 2.5 meters deep and 95 meters long; the tank also employs a 6-paddle wavemaker which can generate programmable surface waves. A 155-cm-long model boat weighing 6.5 kilograms was automatically dragged on the surface of the tank via an electrical towing mechanism. The movement of the model boat along the fiber cable and over the hydrophone was recorded using a commercially available NEC Distributed Acoustic Sensing (DAS) system and simultaneously by a hydrophone. The experiments were repeated with and without the artificially generated surface waves. The data obtained from the hydrophone and the DAS system are presented and compared. The results show the compatibility between the DAS data and the hydrophone data. More importantly, ourresults show that it is possible to measure the surface waves and to detect a surface vessel approaching the sensor by only using the time domain analysis in terms of detected total energy over time.

Resilient DFOS Placement Strategy for Power Grid Monitoring: Integrating Fiber and Power Network Dependencies

We propose a novel Distributed Fiber Optic Sensing (DFOS) placement strategy tailored to the evolving needs of modern power grids, where fiber cables serve dual purposes: communication and real-time sensing. Our approach integrates a heuristic algorithm, PURE (Power Source-aware Route Exploration), with Integer Linear Programming (ILP) to optimize DFOS placement while addressing power supply constraints. The strategy ensures resilient monitoring across diverse grid scenarios by prioritizing observability during outages and leveraging advancements in fiber infrastructure deployment. Case studies demonstrate the effectiveness of our methodology in maintaining power grid resilience while minimizing deployment costs.

NEC Labs America Joins CS3 Advisory Board to Advance Smart Streetscapes

NEC Laboratories America has joined the Center for Smart Streetscapes (CS3) Advisory Board, a National Science Foundation–funded initiative advancing urban innovation through technology, data, and design. As a leader in AI, computer vision, and edge computing, NEC Labs America will collaborate with researchers, civic leaders, and industry partners to develop intelligent infrastructure that enhances safety, accessibility, and efficiency in public spaces.