Get started
Author

Robert Kirk

Observed name: Kirk, Robert
Observed institution: University College London
OpenAlex ID: A5134766128
Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks
2026 · Souly, Alexandra, Fronsdal, Kai, et al. · arXiv (Cornell University)
PDF
Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds
2026 · Ahlqvist, Axel, Guan, Richard, et al. · arXiv (Cornell University)
PDF
Prefill Awareness in Large Language Models
2026 · Wang, Andy, Mahajan, Parv, et al. · arXiv (Cornell University)
PDF
EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models
2026 · Li, Xinning, Ochwang'i, Kemunto, et al. · arXiv (Cornell University)
PDF
Evaluating whether AI models would sabotage AI safety research
2026 · Kirk, Robert, Souly, Alexandra, et al. · arXiv (Cornell University)
PDF
Propensity Inference: Environmental Contributors to LLM Behaviour
2026 · Järviniemi, Olli, Makins, Oliver, et al. · arXiv (Cornell University)
PDF
UK AISI Alignment Evaluation Case-Study
2026 · Souly, Alexandra, Kirk, Robert, et al. · arXiv (Cornell University)
PDF
STACK: Adversarial Attacks on LLM Safeguard Pipelines
2026 · Ian R. McKenzie, Oskar John Hollinsworth, et al. · Proceedings of the AAAI Conference on Artificial Intelligence
Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions
2026 · Rosser, J, Kirk, Robert, et al. · arXiv (Cornell University)
PDF
1174 - STACK: Adversarial Attacks on LLM Safeguard Pipelines
2026 · Association for Artificial Intelligence 2026, Casper, Stephen, et al. · Underline Science Inc.
STACK: Adversarial Attacks on LLM Safeguard Pipelines
2026 · Association for Artificial Intelligence 2026, Casper, Stephen, et al. · Underline Science Inc.
Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs
2025 · Xander Davies, Eric Winsor, et al. · neural information processing systems
PDF
Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
2025 · Andy Zou, Maxwell Lin, et al. · neural information processing systems
Works count: 14
Citation count:
H-index:
I10-index:
Year
Topic
Type