Related papers: SCI: An Equilibrium for Signal Intelligence

Related papers

Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations [55.76952683833966]
This paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC) to reduce confidence set size when data may be corrupted.<n>Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size.
arXiv Detail & Related papers (2026-07-29T05:16:59Z)
Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study [0.0]
We quantify the trustworthiness cost of domain adaptation across three SLM architectures (TinyLlama 1B, Gemma-2B, Llama 3.2 1B) and three domains (healthcare, legal, finance)<n>Four fine-tuning strategies (baseline LoPO, Safety-DPO,.<n>Dark ER and TA-LoRA) were evaluated across all 216 experimental configurations with three random seeds.
arXiv Detail & Related papers (2026-07-23T21:54:58Z)
Swarm-Driven Multi-Agent Reasoning for Smart City Security [5.880950534553082]
This work presents TPSC-Sec, an LLM-based multi-agent approach for stable security reasoning in smart cities.<n>TPSC-Sec decomposes analysis across specialized agents that inspect traffic behavior, protocol interactions, identity usage, and temporal attack progression.<n>Experiments over 500 runs show that TPSC-Sec achieves a high consensus acceptance rate of 0.97 plus or minus 0.02.
arXiv Detail & Related papers (2026-07-03T23:04:48Z)
Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning [81.57028614960576]
We show that the Confidence Region possesses two critical properties: 1) High Reliability -- answers in the confidence region become highly accurate and stable, and 2) High Redundancy -- models generate unnecessary tokens long after reaching the correct answer.<n>These properties unlock more efficient and reliable inference strategies.
arXiv Detail & Related papers (2026-06-01T10:11:14Z)
SL-BiLEM: Structured Learnable Behavior-in-the-Loop Epidemic Modeling for Forecasting and Policy Evaluation [42.644852156101685]
Epidemic forecasting faces a fundamental challenge: human behavior dynamically responds to disease spread.<n>We propose textbfSL-BiLEM (Structured Learnable Behavior-in-the-Loop Epidemic Model), leveraging physical constraints as regularization for robust extrapolation.
arXiv Detail & Related papers (2026-05-26T08:46:04Z)
Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
arXiv Detail & Related papers (2026-05-20T19:08:38Z)
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
arXiv Detail & Related papers (2026-04-07T17:43:18Z)
Inference Headroom Ratio: A Diagnostic and Control Framework for Inference Stability Under Constraint [0.0]
Inference Headroom Ratio (IHR) is dimensionless diagnostic quantity for characterizing inference stability in constrained decision systems.<n>IHR formalizes the relationship between a system's effective inferential capacity C and the combined uncertainty and constraint load U + K imposed by its operating environment.
arXiv Detail & Related papers (2026-03-25T22:21:06Z)
Severe Domain Shift in Skeleton-Based Action Recognition:A Study of Uncertainty Failure in Real-World Gym Environments [0.0]
We present a systematic study of a severe domain shift using a novel Gym2D dataset and the UCF101 dataset.<n>Our work challenges standard deployment assumptions, providing a principled safety analysis of both semantic and geometric skeleton recognition deployment.
arXiv Detail & Related papers (2026-03-16T17:37:17Z)
Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework [1.9180507495574395]
Deep Reinforcement Learning (DRL) agents achieve remarkable performance in continuous control but remain opaque, hindering deployment in safety-critical domains.<n>Existing explainability methods either provide only local insights (SHAP, LIME) or employ oversimplified surrogates failing to capture continuous dynamics.<n>This work proposes a Fuzzy System (FCS) distilling neural policies into human-readable IF-THEN rules through K-Means clustering for state-readable partitioning.<n>Three quantifiable metrics are introduced: Rule Density (FRAD) measuring explanation focus, Fuzzy Set Coverage (FSC) validating vocabulary completeness, and Action Space Granularity (
arXiv Detail & Related papers (2026-02-24T23:53:01Z)
BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
arXiv Detail & Related papers (2026-02-19T08:31:16Z)
Complex-Valued Unitary Representations as Classification Heads for Improved Uncertainty Quantification in Deep Neural Networks [1.932555230783329]
Modern deep neural networks achieve high predictive accuracy but remain poorly calibrated.<n>We propose a quantum-inspired classification head architecture that projects backbone features into a complex-valued space.<n>Our ablation study on CIFAR-10 reveals that the unitary magnitude head (complex features evolved under a Cayley unitary, read out via magnitude and softmax) achieves an Expected Error (ECE) of 0.0146, representing a 2.4x improvement over a standard softmax head.<n>Surprisingly, replacing the softmax readout with a Hilbert rule measurement layer - the quantum-mechanically motivated approach - degrades calibration to an ECE of 0.0819
arXiv Detail & Related papers (2026-02-17T00:45:27Z)
Temperature Scaling Attack Disrupting Model Confidence in Federated Learning [4.863985119779627]
We present the Temperature Scaling Attack (TSA), a training-time attack that degrades calibration while preserving accuracy.<n>Our results establish calibration integrity as a critical attack surface in federated learning.
arXiv Detail & Related papers (2026-02-06T12:01:54Z)
Targeted Synthetic Control Method [46.581034704333746]
We introduce the targeted synthetic control (TSC) method, a new two-stage estimator that directly estimates the counterfactual outcome.<n>TSC is flexible and can be instantiated with arbitrary machine learning models.
arXiv Detail & Related papers (2026-02-04T14:38:58Z)
Tri-LLM Cooperative Federated Zero-Shot Intrusion Detection with Semantic Disagreement and Trust-Aware Aggregation [5.905949608791961]
This paper introduces a semantics-driven federated IDS framework that incorporates language-derived semantic supervision into federated optimization.<n>The framework achieves over 80% zero-shot detection accuracy on unseen attack patterns, improving zero-day discrimination by more than 10% compared to similarity-based baselines.
arXiv Detail & Related papers (2026-01-30T16:38:05Z)
Recursive Knowledge Synthesis for Multi-LLM Systems: Stability Analysis and Tri-Agent Audit Framework [0.0]
This paper presents a tri-agent cross-validation framework for analyzing stability and explainability in large language systems.<n>The architecture integrates three heterogeneous LLMs used for semantic generation, analytical consistency checking, and transparency auditing.
arXiv Detail & Related papers (2025-12-17T16:42:45Z)
Efficient Thought Space Exploration through Strategic Intervention [54.35208611253168]
We propose a novel Hint-Practice Reasoning (HPR) framework that operationalizes this insight through two synergistic components.<n>The framework's core innovation lies in Distributional Inconsistency Reduction (DIR), which dynamically identifies intervention points.<n> Experiments across arithmetic and commonsense reasoning benchmarks demonstrate HPR's state-of-the-art efficiency-accuracy tradeoffs.
arXiv Detail & Related papers (2025-11-13T07:26:01Z)
Logistic-Gated Operators Enable Auditable Unit-Aware Thresholds in Symbolic Regression [3.2657452368624678]
logistic-gated operators (LGO) are differentiable gates with learnable location and steepness.<n>On predominantly smooth tasks, gates are pruned, preserving parsimony.<n>The result is compact symbolic equations with explicit, unit-aware thresholds that can be audited against clinical anchors.
arXiv Detail & Related papers (2025-10-05T16:04:47Z)
FedSSG: Expectation-Gated and History-Aware Drift Alignment for Federated Learning [4.175654562922818]
FedSSG is an optima-guided sampling-guided, history-aware drift alignment method.<n>FedSSG consistently outperforms strong drift-aware baselines and accelerates convergence.
arXiv Detail & Related papers (2025-09-17T10:43:05Z)
From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification [9.17282078449475]
We study symbolic surrogate modeling of frozen Transformer embeddings to obtain compact, auditable classifiers with calibrated probabilities.<n>For five benchmarks (SST2G, 20NG, MNIST, CIFAR10, MSC17), embeddings from ModernBERT, DINOv2, and SigLIP are partitioned on the training set into disjoint, information-preserving views.<n>A cooperative multi-population genetic program (MEGP) then learns additive, closed-form logit programs over these views.
arXiv Detail & Related papers (2025-09-16T02:17:04Z)
GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs [56.93583799109029]
GrAInS is an inference-time steering approach that operates across both language-only and vision-language models and tasks.<n>During inference, GrAInS hidden activations at transformer layers guided by token-level attribution signals, and normalizes activations to preserve representational scale.<n>It consistently outperforms both fine-tuning and existing steering baselines.
arXiv Detail & Related papers (2025-07-24T02:34:13Z)
Explainable Vulnerability Detection in C/C++ Using Edge-Aware Graph Attention Networks [0.2499907423888049]
This paper presents ExplainVulD, a graph-based framework for vulnerability detection in C/C++ code.<n>It achieves a mean accuracy of 88.25 percent and an F1 score of 48.23 percent across 30 independent runs on the ReVeal dataset.
arXiv Detail & Related papers (2025-07-22T12:49:14Z)
Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis [55.13545823385091]
Federated reinforcement learning (FedRL) enables collaborative learning while preserving data privacy by preventing direct data exchange between agents.<n>In real-world applications, each agent may experience slightly different transition dynamics, leading to inherent model mismatches.<n>We show that even moderate levels of information sharing significantly mitigate environment-specific errors.
arXiv Detail & Related papers (2025-03-21T18:06:28Z)
Robustness and Accuracy Could Be Reconcilable by (Proper) Definition [109.62614226793833]
The trade-off between robustness and accuracy has been widely studied in the adversarial literature. We find that it may stem from the improperly defined robust error, which imposes an inductive bias of local invariance. By definition, SCORE facilitates the reconciliation between robustness and accuracy, while still handling the worst-case uncertainty.
arXiv Detail & Related papers (2022-02-21T10:36:09Z)
Coalitional Bayesian Autoencoders -- Towards explainable unsupervised deep learning [78.60415450507706]
We show that explanations of BAE's predictions suffer from high correlation resulting in misleading explanations. To alleviate this, a "Coalitional BAE" is proposed, which is inspired by agent-based system theory. Our experiments on publicly available condition monitoring datasets demonstrate the improved quality of explanations using the Coalitional BAE.
arXiv Detail & Related papers (2021-10-19T15:07:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.