Cover Image

AI Control: Improving Safety Despite Intentional Subversion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Greenblatt, Ryan, Shlegeris, Buck, Sachan, Kshitij, Roger, Fabien
Format:	Preprint
Published:	2023
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Polysemanticity and Capacity in Neural Networks
by: Scherlis, Adam, et al.
Published: (2022)

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

Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?
by: Mallen, Alex, et al.
Published: (2024)

Language models are better than humans at next-token prediction
by: Shlegeris, Buck, et al.
Published: (2022)

Stress-Testing Capability Elicitation With Password-Locked Models
by: Greenblatt, Ryan, et al.
Published: (2024)

Ctrl-Z: Controlling AI Agents via Resampling
by: Bhatt, Aryan, et al.
Published: (2025)

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

Improving Large Language Model Safety with Contrastive Representation Learning
by: Simko, Samuel, et al.
Published: (2025)

Alignment faking in large language models
by: Greenblatt, Ryan, et al.
Published: (2024)

Do Unlearning Methods Remove Information from Language Model Weights?
by: Deeb, Aghyad, et al.
Published: (2024)

Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation
by: Canavan, Callum, et al.
Published: (2026)

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
by: Hubinger, Evan, et al.
Published: (2024)

Self-Attribution Bias: When AI Monitors Go Easy on Themselves
by: Khullar, Dipika, et al.
Published: (2026)

Steering Language Models with Weight Arithmetic
by: Fierro, Constanza, et al.
Published: (2025)

What Do Language Models Learn in Context? The Structured Task Hypothesis
by: Li, Jiaoda, et al.
Published: (2024)

The Persistence of Neural Collapse Despite Low-Rank Bias
by: Garrod, Connall, et al.
Published: (2024)

Safety-Critical Traffic Simulation with Adversarial Transfer of Driving Intentions
by: Huang, Zherui, et al.
Published: (2025)

VRU-CIPI: Crossing Intention Prediction at Intersections for Improving Vulnerable Road Users Safety
by: Abdelrahman, Ahmed S., et al.
Published: (2025)

Energy-Guided Data Sampling for Traffic Prediction with Mini Training Datasets
by: Yang, Zhaohui, et al.
Published: (2024)

DiFR: Inference Verification Despite Nondeterminism
by: Karvonen, Adam, et al.
Published: (2025)

A physics-informed U-Net-LSTM network for nonlinear structural response under seismic excitation
by: Biswas, Sutirtha, et al.
Published: (2025)

ProPACT: A Proactive AI-Driven Adaptive Collaborative Tutor for Pair Programming
by: Golrang, Anahita, et al.
Published: (2026)

Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference
by: Xue, Anton, et al.
Published: (2024)

Learning-Augmented Robust Algorithmic Recourse
by: Kayastha, Kshitij, et al.
Published: (2024)

Optimal Robust Recourse with $L^p$-Bounded Model Change
by: Kyaw, Phone, et al.
Published: (2025)

Pretrained LLMs as Real-Time Controllers for Robot Operated Serial Production Line
by: Waseem, Muhammad, et al.
Published: (2025)

All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language
by: Guo, Shiyuan, et al.
Published: (2025)

Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing
by: Ozyurt, Yilmazcan, et al.
Published: (2024)

State Your Intention to Steer Your Attention: An AI Assistant for Intentional Digital Living
by: Choi, Juheon, et al.
Published: (2025)

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

Improving Language Models with Intentional Analysis
by: Yin, Yuwei, et al.
Published: (2025)

Excess Description Length of Learning Generalizable Predictors
by: Donoway, Elizabeth, et al.
Published: (2026)

Optimality of Sub-network Laplace Approximations: New Results and Methods
by: Raha, Swarnali, et al.
Published: (2026)

Tabular and Deep Reinforcement Learning for Gittins Index
by: Dhankhar, Harshit, et al.
Published: (2024)

Online Intention Prediction via Control-Informed Learning
by: Zhou, Tianyu, et al.
Published: (2026)

A Framework for Evaluating Faithfulness in Explainable AI for Machine Anomalous Sound Detection Using Frequency-Band Perturbation
by: Buck, Alexander, et al.
Published: (2026)

Structured Sparsity and Weight-adaptive Pruning for Memory and Compute efficient Whisper models
by: Mudi, Prasenjit K, et al.
Published: (2025)

What Makes Local Updates Effective: The Role of Data Heterogeneity and Smoothness
by: Patel, Kumar Kshitij
Published: (2025)

Auto-Adaptive PINNs with Applications to Phase Transitions
by: Buck, Kevin, et al.
Published: (2025)

A Modular, Data-Free Pipeline for Multi-Label Intention Recognition in Transportation Agentic AI Applications
by: Zhang, Xiaocai, et al.
Published: (2025)