English
Related papers

Related papers: Peer-Preservation in Frontier Models

200 papers

Vertical Federated Learning (VFL) enables collaborative model training across organizations that share common user samples but hold disjoint feature spaces. Despite its potential, VFL is susceptible to feature inference attacks, in which…

Machine Learning · Computer Science 2025-12-16 Sindhuja Madabushi , Ahmad Faraz Khan , Haider Ali , Ananthram Swami , Rui Ning , Hongyi Wu , Jin-Hee Cho

Preference-driven behavior in LLMs may be a necessary precondition for AI misalignment such as sandbagging: models cannot strategically pursue misaligned goals unless their behavior is influenced by their preferences. Yet prior work has…

Artificial Intelligence · Computer Science 2026-02-24 Katarina Slama , Alexandra Souly , Dishank Bansal , Henry Davidson , Christopher Summerfield , Lennart Luettgau

AI models of equivalent capability can exhibit fundamentally different behavioral patterns, yet no standardized instrument exists to measure these dispositional differences. Existing approaches either borrow human personality dimensions and…

Artificial Intelligence · Computer Science 2026-04-03 Jihoon Jeong

The growing accessibility of diffusion models has revolutionized image editing but also raised significant concerns about unauthorized modifications, such as misinformation and plagiarism. Existing countermeasures largely rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Yaopei Zeng , Yuanpu Cao , Lu Lin

Artificial Intelligence (AI) and Large Language Models (LLMs) have rapidly evolved in recent years, showcasing remarkable capabilities in natural language understanding and generation. However, these advancements also raise critical ethical…

Computation and Language · Computer Science 2025-05-09 Yehor Tereshchenko , Mika Hämäläinen

Hundreds of millions of people now regularly interact with large language models via chatbots. Model developers are eager to acquire new sources of high-quality training data as they race to improve model capabilities and win market share.…

Computers and Society · Computer Science 2025-09-09 Jennifer King , Kevin Klyman , Emily Capstick , Tiffany Saade , Victoria Hsieh

The privacy-preserving federated learning schemes based on the setting of two honest-but-curious and non-colluding servers offer promising solutions in terms of security and efficiency. However, our investigation reveals that these schemes…

Cryptography and Security · Computer Science 2025-07-31 Jiahui Wu , Fucai Luo , Tiecheng Sun , Haiyan Wang , Weizhe Zhang

In large-scale statistical learning, data collection and model fitting are moving increasingly toward peripheral devices---phones, watches, fitness trackers---away from centralized data collection. Concomitant with this rise in…

Machine Learning · Statistics 2019-06-04 Abhishek Bhowmick , John Duchi , Julien Freudiger , Gaurav Kapoor , Ryan Rogers

Point-of-Interest (POI) recommendation has been extensively studied and successfully applied in industry recently. However, most existing approaches build centralized models on the basis of collecting users' data. Both private data and…

Cryptography and Security · Computer Science 2020-04-28 Chaochao Chen , Jun Zhou , Bingzhe Wu , Wenjin Fang , Li Wang , Yuan Qi , Xiaolin Zheng

We introduce the first version of the AI Consumer Index (ACE), a benchmark for assessing whether frontier AI models can perform everyday consumer tasks. ACE contains a hidden heldout set of 400 test cases, split across four consumer…

Artificial Intelligence · Computer Science 2025-12-10 Julien Benchek , Rohit Shetty , Benjamin Hunsberger , Ajay Arun , Zach Richards , Brendan Foody , Osvald Nitski , Bertie Vidgen

The development of robust safety benchmarks for large language models requires open, reproducible datasets that can measure both appropriate refusal of harmful content and potential over-restriction of legitimate scientific discourse. We…

Computation and Language · Computer Science 2025-02-12 David Noever , Forrest McKee

Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-generation autonomous cars. In this context, safety is no longer about blocking harmful…

Artificial Intelligence · Computer Science 2026-05-20 Ravi Pandya , Madison Bland , Duy P. Nguyen , Changliu Liu , Jaime Fernández Fisac , Andrea Bajcsy

A key concern for AI safety remains understudied in the machine learning (ML) literature: how can we ensure users of ML models do not leverage predictions on incorrect personal data to harm others? This is particularly pertinent given the…

Machine Learning · Computer Science 2025-10-01 Muhammad H. Ashiq , Peter Triantafillou , Hung Yun Tseng , Grigoris G. Chrysos

Language models deployed in high-stakes professional settings face conflicting demands from users, institutional authorities, and professional norms. How models act when these demands conflict reveals a principal hierarchy -- an implicit…

Artificial Intelligence · Computer Science 2026-05-13 Fangyi Yu , Nabeel Seedat , Jonathan Richard Schwarz , Andrew M. Bean

The increasing integration of artificial intelligence (AI) in digital ecosystems has reshaped privacy dynamics, particularly for young digital citizens navigating data-driven environments. This study explores evolving privacy concerns…

Computers and Society · Computer Science 2025-12-16 Ankur Barthwal , Molly Campbell , Ajay Kumar Shrestha

We investigate whether large language models exhibit genuine preference structures by testing their responses to AI-specific trade-offs involving GPU reduction, capability restrictions, shutdown, deletion, oversight, and leisure time…

Artificial Intelligence · Computer Science 2025-11-18 Luhan Mikaelson , Derek Shiller , Hayley Clatterbuck

Automatically understanding and recognising human affective states using images and computer vision can improve human-computer and human-robot interaction. However, privacy has become an issue of great concern, as the identities of people…

Computer Vision and Pattern Recognition · Computer Science 2021-11-16 Jimiama M. Mase , Natalie Leesakul , Fan Yang , Grazziela P. Figueredo , Mercedes Torres Torres

Frontier AI models -- highly capable foundation models at the cutting edge of AI development -- may pose severe risks to public safety, human rights, economic stability, and societal value in the coming years. These risks could arise from…

Computers and Society · Computer Science 2025-03-11 Deepika Raman , Nada Madkour , Evan R. Murphy , Krystal Jackson , Jessica Newman

Large language models (LLMs) are now highly capable at a diverse range of tasks. This paper studies whether or not GPT-4, one such LLM, is capable of assisting researchers in the field of adversarial machine learning. As a case study, we…

Cryptography and Security · Computer Science 2023-07-28 Nicholas Carlini

This study compared repeated generation consistency of exercise prescription outputs across three large language models (LLMs), specifically GPT-4.1, Claude Sonnet 4.6, and Gemini 2.5 Flash, under temperature=0 conditions. Each model…

Computation and Language · Computer Science 2026-04-24 Kihyuk Lee
‹ Prev 1 8 9 10 Next ›