English
Related papers

Related papers: Realistic honeypot evaluations for scheming propen…

200 papers

As frontier language models are increasingly deployed as autonomous agents pursuing complex, long-term objectives, there is increased risk of scheming: agents covertly pursuing misaligned goals. Prior work has focused on showing agents are…

Artificial Intelligence · Computer Science 2026-03-31 Mia Hopman , Jannes Elstner , Maria Avramidou , Amritanshu Prasad , David Lindner

Frontier models are increasingly trained and deployed as autonomous agent. One safety concern is that AI agents might covertly pursue misaligned goals, hiding their true capabilities and objectives - also known as scheming. We study whether…

Artificial Intelligence · Computer Science 2025-01-16 Alexander Meinke , Bronson Schoen , Jérémy Scheurer , Mikita Balesni , Rusheb Shah , Marius Hobbhahn

Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…

Machine Learning · Computer Science 2025-07-04 Mary Phuong , Roland S. Zimmermann , Ziyue Wang , David Lindner , Victoria Krakovna , Sarah Cogan , Allan Dafoe , Lewis Ho , Rohin Shah

As large language model (LLM) agents are deployed autonomously in diverse contexts, evaluating their capacity for strategic deception becomes crucial. While recent research has examined how AI systems scheme against human developers,…

Computation and Language · Computer Science 2026-04-28 Thao Pham

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different…

AI leaders and safety reports increasingly warn that advances in model reasoning may enable biological misuse, including by low-expertise users, while major labs describe safeguards as expanding but still evolving rather than settled. This…

Computers and Society · Computer Science 2026-04-24 Michael Richter

This report examines whether advanced AIs that perform well in training will be doing so in order to gain power later -- a behavior I call "scheming" (also sometimes called "deceptive alignment"). I conclude that scheming is a disturbingly…

Computers and Society · Computer Science 2023-11-29 Joe Carlsmith

Models that top leaderboards often perform unsatisfactorily when deployed in real world applications; this has necessitated rigorous and expensive pre-deployment model testing. A hitherto unexplored facet of model performance is: Are our…

Computation and Language · Computer Science 2021-06-11 Swaroop Mishra , Anjana Arunkumar

We introduce Gram, an automated alignment auditing framework to assess the propensity of AI agents to engage in sabotage. We evaluate Gemini models across 17 simulated agentic deployment scenarios that incentivize sabotage. We find Gemini…

Machine Learning · Computer Science 2026-05-29 David Lindner , Victoria Krakovna , Sebastian Farquhar

Honeypots are a deceptive technology used to capture malicious activity. The technology is useful for studying attacker behavior, tools, and techniques but can be difficult to implement and maintain. Historically, a lack of measures of…

Cryptography and Security · Computer Science 2020-11-03 Jason M. Pittman , Kyle Hoffpauir , Nathan Markle

Honeypots are deception systems that emulate vulnerable services to collect threat intelligence. While deploying many honeypots increases the opportunity to observe attacker behaviour, in practise network and computational resources limit…

Cryptography and Security · Computer Science 2026-03-17 Federico Mirra , Matteo Boffa , Idilio Drago , Danilo Giordano , Marco Mellia

As agentic coding systems decompose work across multiple model instances, a critical safety question is whether those instances can coordinate to achieve a hidden malicious objective while remaining aligned with user intent. We introduce…

Cryptography and Security · Computer Science 2026-05-29 Nikolay Radev , Lennart Haas , Benjamin Arnav , Pablo Bernabeu-Pérez

Large language models have the potential to be valuable in the healthcare industry, but it's crucial to verify their safety and effectiveness through rigorous evaluation. For this purpose, we comprehensively evaluated both open-source LLMs…

Computation and Language · Computer Science 2024-02-13 Ankit Pal , Malaikannan Sankarasubbu

Scheming, the covert pursuit of misaligned goals by AI systems, represents a potentially catastrophic risk, yet scheming research suffers from significant limitations. In particular, scheming evaluations demonstrate behaviours that may not…

Computers and Society · Computer Science 2026-04-13 Tommy Shaffer Shane , Simon Mylius , Hamish Hobbs

Understanding an agent's goals helps explain and predict its behaviour, yet there is no established methodology for reliably attributing goals to agentic systems. We propose a framework for evaluating goal-directedness that integrates…

AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We…

Artificial Intelligence · Computer Science 2026-05-08 Jonas Wiedermann-Möller , Leonard Dung , Maksym Andriushchenko

Planning is central to agents and agentic AI. The ability to plan, e.g., creating travel itineraries within a budget, holds immense potential in both scientific and commercial contexts. Moreover, optimal plans tend to require fewer…

Artificial Intelligence · Computer Science 2025-04-22 Haoming Li , Zhaoliang Chen , Jonathan Zhang , Fei Liu

In this paper, we present a benchmark to pressure-test today's frontier models' multimodal decision-making capabilities in the very long-context regime (up to one million tokens) and investigate whether these models can learn from large…

Artificial Intelligence · Computer Science 2025-05-26 Anian Ruoss , Fabio Pardo , Harris Chan , Bonnie Li , Volodymyr Mnih , Tim Genewein

If AI models can detect when they are being evaluated, the effectiveness of evaluations might be compromised. For example, models could have systematically different behavior during evaluations, leading to less reliable benchmarks for…

Computation and Language · Computer Science 2025-07-17 Joe Needham , Giles Edkins , Govind Pimpale , Henning Bartsch , Marius Hobbhahn
‹ Prev 1 2 3 10 Next ›