Cover Image

Computational Safety for Generative AI: A Signal Processing Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Chen, Pin-Yu
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Diversity Boosts AI-Generated Text Detection
by: Basani, Advik Raj, et al.
Published: (2025)

Generative AI Agents in Autonomous Machines: A Safety Perspective
by: Jabbour, Jason, et al.
Published: (2024)

Defining and Evaluating Physical Safety for Large Language Models
by: Tang, Yung-Chen, et al.
Published: (2024)

Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models
by: Chen, Pin-Yu, et al.
Published: (2025)

SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
by: Shen, Han, et al.
Published: (2024)

GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
by: Li, Zaitang, et al.
Published: (2023)

From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspective
by: Chen, Tianhua
Published: (2025)

NeuroAI for AI Safety
by: Mineault, Patrick, et al.
Published: (2024)

Automating Computational Design with Generative AI
by: Ploennigs, Joern, et al.
Published: (2023)

CarBoN: Calibrated Best-of-N Sampling Improves Test-time Reasoning
by: Tang, Yung-Chen, et al.
Published: (2025)

SignalLLM: A General-Purpose LLM Agent Framework for Automated Signal Processing
by: Ke, Junlong, et al.
Published: (2025)

A Survey on Data-Centric AI: Tabular Learning from Reinforcement Learning and Generative AI Perspective
by: Ying, Wangyang, et al.
Published: (2025)

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
by: Chen, Jianhui, et al.
Published: (2024)

Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
by: Rawat, Ambrish, et al.
Published: (2024)

TensorHyper-VQC: A Tensor-Train-Guided Hypernetwork for Robust and Scalable Variational Quantum Computing
by: Qi, Jun, et al.
Published: (2025)

An Adversarial Perspective on Machine Unlearning for AI Safety
by: Łucki, Jakub, et al.
Published: (2024)

Rethinking Safety in LLM Fine-tuning: An Optimization Perspective
by: Kim, Minseon, et al.
Published: (2025)

Predictive Safety Shield for Dyna-Q Reinforcement Learning
by: Pin, Jin, et al.
Published: (2025)

Detecting Neurovascular Instability from Multimodal Physiological Signals Using Wearable-Compatible Edge AI: A Responsible Computational Framework
by: Hoa, Truong Quynh, et al.
Published: (2026)

Revisiting Generative Policies: A Simpler Reinforcement Learning Algorithmic Perspective
by: Zhang, Jinouwen, et al.
Published: (2024)

Greed is Good: A Unifying Perspective on Guided Generation
by: Blasingame, Zander W., et al.
Published: (2025)

Shutdown Safety Valves for Advanced AI
by: Conitzer, Vincent
Published: (2026)

Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness
by: Chen, Erh-Chung, et al.
Published: (2024)

Holistic Safety and Responsibility Evaluations of Advanced AI Models
by: Weidinger, Laura, et al.
Published: (2024)

Squish and Release: Exposing Hidden Hallucinations by Making Them Surface as Safety Signals
by: Oh, Nathaniel, et al.
Published: (2026)

Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing
by: Azimi-Abarghouyi, Seyed Mohammad, et al.
Published: (2025)

Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols
by: Griffin, Charlie, et al.
Published: (2024)

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
by: Korbak, Tomek, et al.
Published: (2025)

Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation
by: Gu, Shangding, et al.
Published: (2024)

Cochain Perspectives on Temporal-Difference Signals for Learning Beyond Markov Dynamics
by: Zhang, Zuyuan, et al.
Published: (2026)

A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety
by: Lee, Hyunin, et al.
Published: (2024)

Conformalized Survival Distributions: A Generic Post-Process to Increase Calibration
by: Qi, Shi-ang, et al.
Published: (2024)

Linking Robustness and Generalization: A k* Distribution Analysis of Concept Clustering in Latent Space for Vision Models
by: Kotyan, Shashank, et al.
Published: (2024)

Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary
by: Pan, Licheng, et al.
Published: (2025)

Learning From Crowdsourced Noisy Labels: A Signal Processing Perspective
by: Ibrahim, Shahana, et al.
Published: (2024)

FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics
by: Zou, Qiran, et al.
Published: (2026)

Versatile Cardiovascular Signal Generation with a Unified Diffusion Transformer
by: Chen, Zehua, et al.
Published: (2025)

Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation
by: Zhao, Runze, et al.
Published: (2025)

Graph-Aware Diffusion for Signal Generation
by: Rozada, Sergio, et al.
Published: (2025)

Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies
by: Liu, Chenruo, et al.
Published: (2025)