English
Related papers

Related papers: Honeypot Protocol

200 papers

Black-box safety evaluation of AI systems assumes model behavior on test distributions reliably predicts deployment performance. We formalize and challenge this assumption through latent context-conditioned policies -- models whose outputs…

Artificial Intelligence · Computer Science 2026-02-20 Vishal Srivastava

Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…

Machine Learning · Computer Science 2026-04-02 Aengus Lynch

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for…

Artificial Intelligence · Computer Science 2026-05-12 Pedro Conde , Henrique Branquinho , Valerio Mazzone , Bruno Mendes , André Baptista , Nuno Moniz

The proliferation of insecure Internet-connected devices gave rise to the IoT botnets which can grow very large rapidly and may perform high-impact cyber-attacks. The related studies for tackling IoT botnets are concerned with either…

Cryptography and Security · Computer Science 2021-09-13 Tolijan Trajanovski , Ning Zhang

This paper studies binary hypothesis testing based on measurements from a set of sensors, a subset of which can be compromised by an attacker. The measurements from a compromised sensor can be manipulated arbitrarily by the adversary. The…

Information Theory · Computer Science 2018-01-22 Xiaoqiang Ren , Jiaqi Yan , Yilin Mo

The model of a non-Bayesian agent who faces a repeated game with incomplete information against Nature is an appropriate tool for modeling general agent-environment interactions. In such a model the environment state (controlled by Nature)…

Artificial Intelligence · Computer Science 2014-11-17 D. Monderer , M. Tennenholtz

Learning effective contextual-bandit policies from past actions of a deployed system is highly desirable in many settings (e.g. voice assistants, recommendation, search), since it enables the reuse of large amounts of log data.…

Machine Learning · Computer Science 2020-06-18 Noveen Sachdeva , Yi Su , Thorsten Joachims

We present a novel class of proof-of-position algorithms: Tree-Proof-of-Position (T-PoP). This algorithm is decentralised, collaborative and can be computed in a privacy preserving manner, such that agents do not need to reveal their…

Data Structures and Algorithms · Computer Science 2024-06-05 Aida Manzano Kharman , Pietro Ferraro , Homayoun Hamedmoghadam , Robert Shorten

We consider the contextual bandit problem on general action and context spaces, where the learner's rewards depend on their selected actions and an observable context. This generalizes the standard multi-armed bandit to the case where side…

Machine Learning · Statistics 2023-01-03 Moise Blanchard , Steve Hanneke , Patrick Jaillet

Industrial Operational Technology (OT) systems are increasingly targeted by cyber-attacks due to their integration with Information Technology (IT) systems in the Industry 4.0 era. Besides intrusion detection systems, honeypots can…

Networking and Internet Architecture · Computer Science 2024-10-30 Olaf Sassnick , Georg Schäfer , Thomas Rosenstatter , Stefan Huber

In multi-hop mobile ad hoc networks (MANETs),mobile nodes cooperate with each other without using any infrastructure such as access points or base stations. Security remains a major challenge for these networks due to their features of open…

Cryptography and Security · Computer Science 2011-11-03 Jaydip Sen , M. Girish Chandra , P. Balamuralidhar , Harihara S. G. , Harish Reddy

The steadily increasing level of automation in human-centred systems demands rigorous design methods for analysing and controlling interactions between humans and automated components, especially in safety-critical applications. The…

Human-Computer Interaction · Computer Science 2025-11-19 Mehrnoush Hajnorouzi , Astrid Rakow , Martin Fränzle

We describe a shared control methodology that can, without knowledge of the task, be used to improve a human's control of a dynamic system, be used as a training mechanism, and be used in conjunction with Imitation Learning to generate…

Robotics · Computer Science 2019-05-28 Alexander Broad , Todd Murphey , Brenna Argall

We introduce the cram method as a general statistical framework for evaluating the final learned policy from a multi-armed contextual bandit algorithm, using the dataset generated by the same bandit algorithm. The proposed on-policy…

Machine Learning · Computer Science 2025-04-16 Zeyang Jia , Kosuke Imai , Michael Lingzhi Li

In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal RL solutions for training tasks. This work relates to meta…

Machine Learning · Computer Science 2023-01-04 Sahand Rezaei-Shoshtari , Charlotte Morissette , Francois Robert Hogan , Gregory Dudek , David Meger

Real-world artificial intelligence (AI) systems are increasingly required to operate autonomously in dynamic, uncertain, and continuously changing environments. However, most existing AI models rely on predefined objectives, static training…

Artificial Intelligence · Computer Science 2025-11-04 Hong Su

Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit…

Cryptography and Security · Computer Science 2026-04-20 Xuwei Ding , Skylar Zhai , Linxin Song , Jiate Li , Taiwei Shi , Nicholas Meade , Siva Reddy , Jian Kang , Jieyu Zhao

We introduce a multi-turn benchmark for evaluating personalised alignment in LLM-based AI assistants, focusing on their ability to handle user-provided safety-critical contexts. Our assessment of ten leading models across five scenarios…

Human-Computer Interaction · Computer Science 2025-01-31 Lize Alberts , Benjamin Ellis , Andrei Lupu , Jakob Foerster

Operators performing high-stakes, safety-critical tasks - such as air traffic controllers, surgeons, or mission control personnel - must maintain exceptional cognitive performance under variable and often stressful conditions. This paper…

Human-Computer Interaction · Computer Science 2025-06-30 Maciej Grzeszczuk , Grzegorz Pochwatko , Barbara Karpowicz , Stanisław Knapiński , Wiesław Kopeć

AI systems that learn through reward feedback about the actions they take are increasingly deployed in domains that have significant impact on our daily life. However, in many cases the online rewards should not be the only guiding…

Artificial Intelligence · Computer Science 2018-09-18 Avinash Balakrishnan , Djallel Bouneffouf , Nicholas Mattei , Francesca Rossi