English
Related papers

Related papers: Frontier Models Can Take Actions at Low Probabilit…

200 papers

Adaptively collected data has become ubiquitous within modern practice. However, even seemingly benign adaptive sampling schemes can introduce severe biases, rendering traditional statistical inference tools inapplicable. This can be…

Statistics Theory · Mathematics 2025-12-02 Wei Fan , Kevin Tan , Yuting Wei

High complexity models are notorious in machine learning for overfitting, a phenomenon in which models well represent data but fail to generalize an underlying data generating process. A typical procedure for circumventing overfitting…

Machine Learning · Statistics 2025-03-11 James Schmidt

Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law…

Machine Learning · Computer Science 2026-03-20 Xiangwen Wang , Ananth Balashankar , Varun Chandrasekaran

Chain-of-Thought (CoT) reasoning has significantly advanced state-of-the-art AI capabilities. However, recent studies have shown that CoT reasoning is not always faithful when models face an explicit bias in their prompts, i.e., the CoT can…

Artificial Intelligence · Computer Science 2025-06-18 Iván Arcuschin , Jett Janiak , Robert Krzyzanowski , Senthooran Rajamanoharan , Neel Nanda , Arthur Conmy

Predictive models are often deployed through existing decision policies that stakeholders are reluctant to change unless a risk constraint requires intervention. We study risk-controlled post-processing: given a deterministic baseline…

Machine Learning · Statistics 2026-05-08 Sunay Joshi , Tao Wang , Hamed Hassani , Edgar Dobriban

Chain-of-Thought (CoT) monitoring has emerged as a compelling method for detecting harmful behaviors such as reward hacking for reasoning models, under the assumption that models' reasoning processes are informative of such behaviors. In…

Machine Learning · Computer Science 2026-03-10 Nikolaus Howe , Micah Carroll

Machine learning models are typically deployed in a test setting that differs from the training setting, potentially leading to decreased model performance because of domain shift. If we could estimate the performance that a pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Zeju Li , Konstantinos Kamnitsas , Mobarakol Islam , Chen Chen , Ben Glocker

Many of today's machine learning (ML) systems are built by reusing an array of, often pre-trained, primitive models, each fulfilling distinct functionality (e.g., feature extraction). The increasing use of primitive models significantly…

Cryptography and Security · Computer Science 2018-12-04 Yujie Ji , Xinyang Zhang , Shouling Ji , Xiapu Luo , Ting Wang

Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for what a model…

Computers and Society · Computer Science 2025-11-27 Udari Madhushani Sehwag , Shayan Shabihi , Alex McAvoy , Vikash Sehwag , Yuancheng Xu , Dalton Towers , Furong Huang

We present a non-asymptotic lower bound on the eigenspectrum of the design matrix generated by any linear bandit algorithm with sub-linear regret when the action set has well-behaved curvature. Specifically, we show that the minimum…

Machine Learning · Computer Science 2023-01-10 Debangshu Banerjee , Avishek Ghosh , Sayak Ray Chowdhury , Aditya Gopalan

Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt injections, despite concerted efforts to make them robust. As…

Machine Learning · Computer Science 2025-06-06 Nikolaus Howe , Ian McKenzie , Oskar Hollinsworth , Michał Zajac , Tom Tseng , Aaron Tucker , Pierre-Luc Bacon , Adam Gleave

Successful self-replication under no human assistance is the essential step for AI to outsmart the human beings, and is an early signal for rogue AIs. That is why self-replication is widely recognized as one of the few red line risks of…

Computation and Language · Computer Science 2024-12-18 Xudong Pan , Jiarun Dai , Yihe Fan , Min Yang

The vulnerability of machine learning models to membership inference attacks has received much attention in recent years. However, existing attacks mostly remain impractical due to having high false positive rates, where non-member samples…

Cryptography and Security · Computer Science 2022-04-12 Lauren Watson , Chuan Guo , Graham Cormode , Alex Sablayrolles

Being cautious is crucial for enhancing the trustworthiness of machine learning systems integrated into decision-making pipelines. Although calibrated probabilities help in optimal decision-making, perfect calibration remains unattainable,…

Machine Learning · Computer Science 2024-08-12 Mari-Liis Allikivi , Joonas Järve , Meelis Kull

Fair calibration is a widely desirable fairness criteria in risk prediction contexts. One way to measure and achieve fair calibration is with multicalibration. Multicalibration constrains calibration error among flexibly-defined…

Machine Learning · Computer Science 2023-09-04 William La Cava , Elle Lett , Guangya Wan

Low-rank matrix completion concerns the problem of estimating unobserved entries in a matrix using a sparse set of observed entries. We consider the non-uniform setting where the observed entries are sampled with highly varying…

Machine Learning · Statistics 2024-03-04 Xumei Xi , Christina Lee Yu , Yudong Chen

Frontier artificial intelligence (AI) systems could pose increasing risks to public safety and security. But what level of risk is acceptable? One increasingly popular approach is to define capability thresholds, which describe AI…

Computers and Society · Computer Science 2024-06-24 Leonie Koessler , Jonas Schuett , Markus Anderljung

High success rates on navigation-related tasks do not necessarily translate into reliable decision making by foundation models. To examine this gap, we evaluate current models on six diagnostic tasks spanning three settings: reasoning under…

Artificial Intelligence · Computer Science 2026-04-09 Jua Han , Jaeyoon Seo , Jungbin Min , Sieun Choi , Huichan Seo , Jihie Kim , Jean Oh

Large (vision-)language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to have the model learn a refusal boundary between safe and unsafe, based on the user's…

Cryptography and Security · Computer Science 2026-04-28 Xinhe Wang , Katia Sycara , Yaqi Xie

Reliable uncertainty calibration is essential for safely deploying deep neural networks in high-stakes applications. Deep neural networks are known to exhibit systematic overconfidence, especially under distribution shifts. Although…

Machine Learning · Computer Science 2025-06-12 Achim Hekler , Lukas Kuhn , Florian Buettner
‹ Prev 1 3 4 5 6 7 10 Next ›