Cover Image

TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mahato, Dipesh Tharu, Poudel, Rohan, Dhungana, Pramod
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Deep learning-based fault identification in condition monitoring
by: Dhungana, Hariom, et al.
Published: (2024)

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
by: Tan, Zhewen, et al.
Published: (2026)

CourtGuard: A Model-Agnostic Framework for Zero-Shot Policy Adaptation in LLM Safety
by: Suleymanov, Umid, et al.
Published: (2026)

SafeSeek: Universal Attribution of Safety Circuits in Language Models
by: Yu, Miao, et al.
Published: (2026)

When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models
by: Hossain, Ismail, et al.
Published: (2026)

Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning
by: Wang, Tongxi, et al.
Published: (2026)

DriftXpress: Faster Drifting Models via Projected RKHS Fields
by: Falahati, Ali, et al.
Published: (2026)

UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models
by: Oh, Sejoon, et al.
Published: (2024)

Empirical Validation of the Classification-Verification Dichotomy for AI Safety Gates
by: Scrivens, Arsenios
Published: (2026)

Information-Theoretic Limits of Safety Verification for Self-Improving Systems
by: Scrivens, Arsenios
Published: (2026)

Guarding the Meaning: Self-Supervised Training for Semantic Robustness in Guard Models
by: Pinneri, Cristina, et al.
Published: (2025)

Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits
by: Elboher, Yizhak Yisrael, et al.
Published: (2025)

Stateful KV Cache Management for LLMs: Balancing Space, Time, Accuracy, and Positional Fidelity
by: Poudel, Pratik
Published: (2025)

Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Models
by: Poudel, Bibek, et al.
Published: (2021)

TriP-LLM: A Tri-Branch Patch-wise Large Language Model Framework for Time-Series Anomaly Detection
by: Yu, Yuan-Cheng, et al.
Published: (2025)

On the Wasserstein Gradient Flow Interpretation of Drifting Models
by: Gretton, Arthur, et al.
Published: (2026)

Bridging Neural ODE and ResNet: A Formal Error Bound for Safety Verification
by: Sayed, Abdelrahman Sayed, et al.
Published: (2025)

Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling
by: Chen, Hao Mark, et al.
Published: (2025)

TARo: Token-level Adaptive Routing for LLM Test-time Alignment
by: Rai, Arushi, et al.
Published: (2026)

AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
by: Liu, Runtao, et al.
Published: (2024)

Latent Guard: a Safety Framework for Text-to-image Generation
by: Liu, Runtao, et al.
Published: (2024)

ETAGE: Enhanced Test Time Adaptation with Integrated Entropy and Gradient Norms for Robust Model Performance
by: Shamsi, Afshar, et al.
Published: (2024)

Test-Time Training Undermines Safety Guardrails
by: Antonelli, Simone, et al.
Published: (2026)

Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization
by: Jian, Chengtao, et al.
Published: (2024)

Using Quality Attribute Scenarios for ML Model Test Case Generation
by: Brower-Sinning, Rachel, et al.
Published: (2024)

Drift Flow Matching
by: Ma, Chenrui, et al.
Published: (2026)

Drift Q-Learning
by: Houssaini, Anas, et al.
Published: (2026)

Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
by: Shao, Shuo, et al.
Published: (2024)

ECHO: Entropy-Confidence Hybrid Optimization for Test-Time Reinforcement Learning
by: Zhao, Chu, et al.
Published: (2026)

An Innovative Next Activity Prediction Using Process Entropy and Dynamic Attribute-Wise-Transformer in Predictive Business Process Monitoring
by: Zare, Hadi, et al.
Published: (2025)

Technical Report: Evaluating Goal Drift in Language Model Agents
by: Arike, Rauno, et al.
Published: (2025)

SymDrift: One-Shot Generative Modeling under Symmetries
by: Darouich, Samir, et al.
Published: (2026)

TLoRA: Tri-Matrix Low-Rank Adaptation of Large Language Models
by: Islam, Tanvir
Published: (2025)

Zero-Shot Attribution for Large Language Models: A Distribution Testing Approach
by: Canonne, Clément L., et al.
Published: (2025)

G-Drift MIA: Membership Inference via Gradient-Induced Feature Drift in LLMs
by: Ranjan, Ravi, et al.
Published: (2026)

FlakyGuard: Automatically Fixing Flaky Tests at Industry Scale
by: Li, Chengpeng, et al.
Published: (2025)

CALM: A Causal Analysis Language Model for Tabular Data in Complex Systems with Local Scores, Conditional Independence Tests, and Relation Attributes
by: Fan, Zhenjiang, et al.
Published: (2025)

Distillation Traps and Guards: A Calibration Knob for LLM Distillability
by: Zhan, Weixiao, et al.
Published: (2026)

Guarding Graph Neural Networks for Unsupervised Graph Anomaly Detection
by: Bei, Yuanchen, et al.
Published: (2024)

Trajectory Guard -- A Lightweight, Sequence-Aware Model for Real-Time Anomaly Detection in Agentic AI
by: Advani, Laksh
Published: (2026)