Imagen de Portada

Robust AI Security and Alignment: A Sisyphean Endeavor?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Vassilev, Apostol
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Arrhythmia Classification from 12-Lead ECG Signals Using Convolutional and Transformer-Based Deep Learning Models
por: Apostol, Andrei, et al.
Publicado: (2025)

Advancements in eHealth Data Analytics through Natural Language Processing and Deep Learning
por: Apostol, Elena-Simona, et al.
Publicado: (2024)

CONTAIN: A Community-based Algorithm for Network Immunization
por: Apostol, Elena-Simona, et al.
Publicado: (2023)

Clone-Robust AI Alignment
por: Procaccia, Ariel D., et al.
Publicado: (2025)

A Novel Reinforcement Learning Model for Post-Incident Malware Investigations
por: Dunsin, Dipo, et al.
Publicado: (2024)

Security-First AI: Foundations for Robust and Trustworthy Systems
por: Tallam, Krti
Publicado: (2025)

The Adaptive Arms Race: Redefining Robustness in AI Security
por: Tsingenopoulos, Ilias, et al.
Publicado: (2023)

AI Alignment: A Comprehensive Survey
por: Ji, Jiaming, et al.
Publicado: (2023)

Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks
por: Xing, Wenpeng, et al.
Publicado: (2025)

GETAE: Graph information Enhanced deep neural NeTwork ensemble ArchitecturE for fake news detection
por: Truică, Ciprian-Octavian, et al.
Publicado: (2024)

Beyond Preferences in AI Alignment
por: Zhi-Xuan, Tan, et al.
Publicado: (2024)

Explainable and Robust Millimeter Wave Beam Alignment for AI-Native 6G Networks
por: Khan, Nasir, et al.
Publicado: (2025)

Measuring AI Alignment with Human Flourishing
por: Hilliard, Elizabeth, et al.
Publicado: (2025)

A Comprehensive Analysis of the Role of Artificial Intelligence and Machine Learning in Modern Digital Forensics and Incident Response
por: Dunsin, Dipo, et al.
Publicado: (2023)

Reinforcement Learning for an Efficient and Effective Malware Investigation during Cyber Incident Response
por: Dunsin, Dipo, et al.
Publicado: (2024)

The AI Alignment Paradox
por: West, Robert, et al.
Publicado: (2024)

Measuring Safety Alignment Effects in Autonomous Security Agents
por: David, Isaac, et al.
Publicado: (2026)

Security of AI Agents
por: He, Yifeng, et al.
Publicado: (2024)

AI Security Map: Holistic Organization of AI Security Technologies and Impacts on Stakeholders
por: Kato, Hiroya, et al.
Publicado: (2025)

Identifying and Mitigating the Security Risks of Generative AI
por: Barrett, Clark, et al.
Publicado: (2023)

Strong Preferences Affect the Robustness of Preference Models and Value Alignment
por: Xu, Ziwei, et al.
Publicado: (2024)

Improved Bounds for Private and Robust Alignment
por: Weng, Wenqian, et al.
Publicado: (2025)

Maia-2: A Unified Model for Human-AI Alignment in Chess
por: Tang, Zhenwei, et al.
Publicado: (2024)

Rethinking AI Cultural Alignment
por: Bravansky, Michal, et al.
Publicado: (2025)

Resource Rational Contractualism Should Guide AI Alignment
por: Levine, Sydney, et al.
Publicado: (2025)

Evaluating Cognitive Age Alignment in Interactive AI Agents
por: Shen, Yifan, et al.
Publicado: (2026)

Dialogical Reasoning Across AI Architectures: A Multi-Model Framework for Testing AI Alignment Strategies
por: Cox, Gray
Publicado: (2026)

Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment
por: Chen, Tiejin, et al.
Publicado: (2026)

Interactive AI Alignment: Specification, Process, and Evaluation Alignment
por: Terry, Michael, et al.
Publicado: (2023)

Secure and Energy-Efficient Wireless Agentic AI Networks
por: Song, Yuanyan, et al.
Publicado: (2026)

Security of and by Generative AI platforms
por: Hayagreevan, Hari, et al.
Publicado: (2024)

The AI Security Pyramid of Pain
por: Ward, Chris M., et al.
Publicado: (2024)

Secure Multiparty Generative AI
por: Shrestha, Manil, et al.
Publicado: (2024)

Robust LLM Alignment via Distributionally Robust Direct Preference Optimization
por: Xu, Zaiyan, et al.
Publicado: (2025)

Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation
por: Li, Yubo, et al.
Publicado: (2025)

Adversarial Preference Learning for Robust LLM Alignment
por: Wang, Yuanfu, et al.
Publicado: (2025)

Manifold Approximation leads to Robust Kernel Alignment
por: Islam, Mohammad Tariqul, et al.
Publicado: (2025)

Doubly Robust Alignment for Large Language Models
por: Xu, Erhan, et al.
Publicado: (2025)

Human-Alignment Influences the Utility of AI-assisted Decision Making
por: Benz, Nina L. Corvelo, et al.
Publicado: (2025)

Neurodivergent Influenceability as a Contingent Solution to the AI Alignment Problem
por: Hernández-Espinosa, Alberto, et al.
Publicado: (2025)