Xander Davies

According to our database, Xander Davies authored at least 22 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

Evaluating whether AI models would sabotage AI safety research.

Robert Kirk, Alexandra Souly, Kai Fronsdal, Abby D'Cruz, Xander Davies

CoRR, April, 2026

UK AISI Alignment Evaluation Case-Study.

Alexandra Souly, Robert Kirk, Jacob Merizian, Abby D'Cruz, Xander Davies

CoRR, April, 2026

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition.

Mateusz Dziemian, Maxwell Lin, Xiaohan Fu, Micha Nowak, Nick Winter, Eliot Krzysztof Jones, Andy Zou, Lama Ahmad, Kamalika Chaudhuri, Sahana Chennabasappa, Xander Davies, Lauren Deason, Benjamin L. Edelman, Tanner Emek, Ivan Evtimov, Jim Gust, Maia Hamin, Kat He, Klaudia Krawiecka, Riccardo Patana, Neil Perry, Troy Peterson, Xiangyu Qi, Javier Rando, Zifan Wang, Zihan Wang, Spencer Whitman, Eric Winsor, Arman Zharmagambetov, Matt Fredrikson, Zico Kolter

CoRR, March, 2026

Boundary Point Jailbreaking of Black-Box LLMs.

Xander Davies, Giorgi Giglemiani, Edmund Lau, Eric Winsor, Geoffrey Irving, Yarin Gal

CoRR, February, 2026

STACK: Adversarial Attacks on LLM Safeguard Pipelines.

Ian R. McKenzie, Oskar John Hollinsworth, Tom Tseng, Xander Davies, Stephen Casper, Aaron David Tucker, Robert Kirk, Adam Gleave

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents.

Julia Bazinska, Max Mathys, Francesco Casucci, Mateo Rojas-Carulla, Xander Davies, Alexandra Souly, Niklas Pfister

CoRR, October, 2025

Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples.

Alexandra Souly, Javier Rando, Ed Chapman, Xander Davies, Burak Hasircioglu, Ezzeldin Shereen, Carlos Mougan, Vasilios Mavroudis, Erik Jones, Chris Hicks, Nicholas Carlini, Yarin Gal, Robert Kirk

CoRR, October, 2025

RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents.

Chengquan Guo, Chulin Xie, Yu Yang, Zhaorun Chen, Zinan Lin, Xander Davies, Yarin Gal, Dawn Song, Bo Li

CoRR, October, 2025

Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs.

Kyle O'Brien, Stephen Casper, Quentin Anthony, Tomek Korbak, Robert Kirk, Xander Davies, Ishan Mishra, Geoffrey Irving, Yarin Gal, Stella Biderman

CoRR, August, 2025

Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition.

Andy Zou, Maxwell Lin, Eliot Krzysztof Jones, Micha Nowak, Mateusz Dziemian, Nick Winter, Alexander Grattan, Valent Nathanael, Ayla Croft, Xander Davies, Jai Patel, Robert Kirk, Nate Burnikell, Yarin Gal, Dan Hendrycks, J. Zico Kolter, Matt Fredrikson

CoRR, July, 2025

Existing Large Language Model Unlearning Evaluations Are Inconclusive.

Zhili Feng, Yixuan Even Xu, Alexander Robey, Robert Kirk, Xander Davies, Yarin Gal, Avi Schwarzschild, J. Zico Kolter

CoRR, June, 2025

An Example Safety Case for Safeguards Against Misuse.

Joshua Clymer, Jonah Weinbaum, Robert Kirk, Kimberly Mai, Selena Zhang, Xander Davies

CoRR, May, 2025

Fundamental Limitations in Defending LLM Finetuning APIs.

Xander Davies, Eric Winsor, Tomek Korbak, Alexandra Souly, Robert Kirk, Christian Schröder de Witt, Yarin Gal

CoRR, February, 2025

Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition.

Andy Zou, Maxwell Lin, Eliot Krzysztof Jones, Micha Nowak, Mateusz Dziemian, Nick Winter, Valent Nathanael, Ayla Croft, Xander Davies, Jai Patel, Robert Kirk, Yarin Gal, Dan Hendrycks, Zico Kolter, Matt Fredrikson

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs.

Xander Davies, Eric Winsor, Alexandra Souly, Tomek Korbak, Robert Kirk, Christian Schroeder de Witt, Yarin Gal

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.

Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas, Maxwell Lin, Justin Wang, Dan Hendrycks, Andy Zou, J. Zico Kolter, Matt Fredrikson, Yarin Gal, Xander Davies

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.

Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas, Maxwell Lin, Justin Wang, Dan Hendrycks, Andy Zou, Zico Kolter, Matt Fredrikson, Eric Winsor, Jerome Wynne, Yarin Gal, Xander Davies

CoRR, 2024

2023

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.

Stephen Casper, Xander Davies, Claudia Shi, Thomas Krendl Gilbert, Jérémy Scheurer, Javier Rando, Rachel Freedman, Tomasz Korbak, David Lindner, Pedro Freire, Tony Tong Wang, Samuel Marks, Charbel-Raphaël Ségerie, Micah Carroll, Andi Peng, Phillip J. K. Christoffersen, Mehul Damani, Stewart Slocum, Usman Anwar, Anand Siththaranjan, Max Nadeau, Eric J. Michaud, Jacob Pfau, Dmitrii Krasheninnikov, Xin Chen, Lauro Langosco, Peter Hase, Erdem Biyik, Anca D. Dragan, David Krueger, Dorsa Sadigh, Dylan Hadfield-Menell

Trans. Mach. Learn. Res., 2023

Circuit Breaking: Removing Model Behaviors with Targeted Ablation.

Maximilian Li, Xander Davies, Max Nadeau

CoRR, 2023

Discovering Variable Binding Circuitry with Desiderata.

Xander Davies, Max Nadeau, Nikhil Prakash, Tamar Rott Shaham, David Bau

CoRR, 2023

Unifying Grokking and Double Descent.

Xander Davies, Lauro Langosco, David Krueger

CoRR, 2023

Sparse Distributed Memory is a Continual Learner.

Trenton Bricken, Xander Davies, Deepak Singh, Dmitry Krotov, Gabriel Kreiman

Proceedings of the Eleventh International Conference on Learning Representations, 2023