Cover Image

On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ball, Sarah, Gluch, Greg, Goldwasser, Shafi, Kreuter, Frauke, Reingold, Omer, Rothblum, Guy N.
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Cryptographic Perspective on Mitigation vs. Detection in Machine Learning
by: Gluch, Greg, et al.
Published: (2025)

How to Verify Any (Reasonable) Distribution Property: Computationally Sound Argument Systems for Distributions
by: Herman, Tal, et al.
Published: (2024)

PINE: Efficient Norm-Bound Verification for Secret-Shared Vectors
by: Rothblum, Guy N., et al.
Published: (2023)

Deniable Encryption in a Quantum World
by: Coladangelo, Andrea, et al.
Published: (2021)

To share or not to share: What risks would laypeople accept to give sensitive data to differentially-private NLP systems?
by: Weiss, Christopher, et al.
Published: (2023)

Planting Undetectable Backdoors in Machine Learning Models
by: Goldwasser, Shafi, et al.
Published: (2022)

Oblivious Defense in ML Models: Backdoor Removal without Detection
by: Goldwasser, Shafi, et al.
Published: (2024)

Accuracy vs. Accuracy: Computational Tradeoffs Between Classification Rates and Utility
by: Amit, Noga, et al.
Published: (2025)

AI Native Asset Intelligence
by: Engelberg, Gal, et al.
Published: (2026)

Local Pan-Privacy for Federated Analytics
by: Feldman, Vitaly, et al.
Published: (2025)

Efficient Public Verification of Private ML via Regularization
by: Bell, Zoë Ruha, et al.
Published: (2025)

Blockchain and AI: Securing Intelligent Networks for the Future
by: Dutta, Joy, et al.
Published: (2026)

Structural Enforcement of Goal Integrity in AI Agents via Separation-of-Powers Architecture
by: Xiang, Rong
Published: (2026)

PREAMBLE: Private and Efficient Aggregation via Block Sparse Vectors
by: Asi, Hilal, et al.
Published: (2025)

Privacy-Preserving Decentralized AI with Confidential Computing
by: Lee, Dayeol, et al.
Published: (2024)

Research on Enhancing Cloud Computing Network Security using Artificial Intelligence Algorithms
by: Wang, Yuqing, et al.
Published: (2025)

Unlocking Apple's Private Cloud Compute: An Analysis of Privacy-Preserving Artificial Intelligence
by: Dittmar, Yannik, et al.
Published: (2026)

Evasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents
by: Aonzo, Simone, et al.
Published: (2026)

ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System
by: Kim, Taesoo, et al.
Published: (2025)

Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
by: Kim, Jinhwa, et al.
Published: (2025)

AI-Powered Algorithms for the Prevention and Detection of Computer Malware Infections
by: Keshava, Rakesh, et al.
Published: (2026)

The Global Impact of AI-Artificial Intelligence: Recent Advances and Future Directions, A Review
by: Pachegowda, Chandregowda
Published: (2023)

Trojans in Artificial Intelligence (TrojAI) Final Report
by: Reese, Kristopher W., et al.
Published: (2026)

Artificial Intelligence for Secured Information Systems in Smart Cities: Collaborative IoT Computing with Deep Reinforcement Learning and Blockchain
by: Far, Amin Zakaie, et al.
Published: (2024)

EdgeShield: A Universal and Efficient Edge Computing Framework for Robust AI
by: Zhong, Duo, et al.
Published: (2024)

When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI
by: Forough, Javad, et al.
Published: (2026)

Cyber Threat Intelligence for Artificial Intelligence Systems
by: Krawczyk, Natalia, et al.
Published: (2026)

Reimagining Safety Alignment with An Image
by: Xia, Yifan, et al.
Published: (2025)

AI-Driven Security in Cloud Computing: Enhancing Threat Detection, Automated Response, and Cyber Resilience
by: Shaffi, Shamnad Mohamed, et al.
Published: (2025)

Evaluating the Reliability and Fidelity of Automated Judgment Systems of Large Language Models
by: Biskupski, Tom, et al.
Published: (2026)

Containment Verification: AI Safety Guarantees Independent of Alignment
by: Moon, Royce, et al.
Published: (2026)

CBPF: Filtering Poisoned Data Based on Composite Backdoor Attack
by: Xia, Hanfeng, et al.
Published: (2024)

Securing Generative AI in Healthcare: A Zero-Trust Architecture Powered by Confidential Computing on Google Cloud
by: Amanna, Adaobi, et al.
Published: (2025)

Emission Impossible: privacy-preserving carbon emissions claims
by: Man, Jessica, et al.
Published: (2025)

Bitcoin-Enhanced Proof-of-Stake Security: Possibilities and Impossibilities
by: Tas, Ertem Nusret, et al.
Published: (2022)

AI-Driven Cyber Threat Intelligence Automation
by: Shah, Shrit, et al.
Published: (2024)

What Was Your Prompt? A Remote Keylogging Attack on AI Assistants
by: Weiss, Roy, et al.
Published: (2024)

Agent Safety Alignment via Reinforcement Learning
by: Sha, Zeyang, et al.
Published: (2025)

EVA: Editing for Versatile Alignment against Jailbreaks
by: Wang, Yi, et al.
Published: (2026)

UK AISI Alignment Evaluation Case-Study
by: Souly, Alexandra, et al.
Published: (2026)