Box Extraction
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software
arXiv:2602.04894v4 Announce Type: replace Abstract: LLMs are increasingly used for code generation, but their outputs often follow recurring templates that can induce predictable vulnerabilities. We study vulnerability persistence in LLM-generated software and introduce Feature--Security Table (FSTab) with two components. First, FSTab enables a black-box attack that predicts likely backend vulnerabilities from observable frontend features and knowledge of the source LLM, without access to...
EML-CD: Causal Mechanism Recovery via EML Symbolic Trees in Structure Learning
arXiv:2606.05942v1 Announce Type: cross Abstract: Neural network (NN)-based nonlinear causal discovery methods recover DAG structure but leave each causal mechanism as a black box. Waxman et al. argued that extracting causal mechanisms from NN weights is ill-posed. We propose EML-CD, a framework that integrates the EML operator (capable of composing elementary functions from a single binary operator) into causal structure learning, with interpretable mechanism recovery as the primary objective.
BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation
Announce Type: replace Abstract: Sequential recommendation systems are widely adopted but often deployed as black-box APIs, which has driven recent interest in model extraction to replicate their capabilities locally. However, the long-tail distribution induces severe signal heterogeneity: dense head sequences trigger the solidification of teacher preference, biasing extraction toward local patterns, while sparse tail sequences yield flat, noisy predictions. Existing one-size-fits-all...
BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation
arXiv:2606.03091v1 Announce Type: new Abstract: Sequential recommendation systems are widely adopted but often deployed as black-box APIs, which has driven recent interest in model extraction to replicate their capabilities locally. However, the long-tail distribution induces severe signal heterogeneity: dense head sequences trigger the solidification of teacher preference, biasing extraction toward local patterns, while sparse tail sequences yield flat, noisy predictions. Existing...
Semantic-decoupled Spatial Partition Guided Point-supervised Oriented Object Detection
arXiv:2506.10601v2 Announce Type: replace Abstract: Given its ability to reduce annotation costs, weakly supervised learning based on single-point annotations has emerged as a research focus in oriented object detection. Compared with the classical teacher-student paradigm, the simple model paradigm (e.g., PointOBB-v2) can substantially further reduce resources required for training while ensuring strong performance.
PolyBuild: An End-to-End Method for Polygonal Building Contour Extraction from High-Resolution Remote Sensing Images
arXiv:2606.08920v1 Announce Type: new Abstract: Extracting building polygon contours from high-resolution remote sensing images is a fundamental task for various mapping applications. However, the presence of varying imaging conditions and complex building structures, makes automatic contour extraction extremely challenging. Mainstream approaches for building extraction often rely on pixel-level segmentation followed by multiple post-processing steps to produce building contour, which can be...
'Don't scare the cat!' Engineers find smarter way to measure quantum systems
'Don't scare the cat!' Engineers find smarter way to measure quantum systems Gaby Clark Scientific Editor Robert Egan Associate Editor UNSW Sydney engineers have riffed on the famous Schrödinger's cat analogy to demonstrate a more efficient way to eliminate errors in quantum computing. "Imagine you're trying to find your cat hiding in one of eight identical cardboard boxes, in a dark and noisy room," says UNSW Scientia Professor Andrea Morello.
Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?
arXiv:2605.30470v1 Announce Type: new Abstract: Graph Machine Learning as a Service (GMLaaS) platforms increasingly implement explainability interfaces to meet regulatory transparency requirements. However, this transparency creates exploitable vulnerabilities for model extraction attacks.
Amortized Neural Optimization for Pre-Layout Signal Integrity Design Space Exploration using Differentiable Surrogates
Announce Type: cross Abstract: Pre-layout design space exploration (DSE) for high-speed signal integrity (SI) analysis is often limited by the computational cost of simulations and iterative optimization algorithms within modern electronic design automation (EDA) workflows. While machine learning surrogate models accelerate the simulation step, optimizing designs still requires utilizing iterative black-box search methods. This iterative nature scales poorly, making multi-corner sweeps...
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP
arXiv:2505.11189v3 Announce Type: replace Abstract: Large language models (LLMs) can amplify misinformation, undermining societal goals such as the UN SDGs. We study three documented drivers of misinformation (valence framing, information overload, and oversimplification) often shaped by default beliefs. Building on evidence that LLMs encode such defaults (e.g., "joy is positive", "math is complex") and can act as "bags of heuristics", we ask whether belief-driven heuristics behind...