Author

Alexandra Souly

Observed name: Souly, Alexandra

Observed institution: University College London

OpenAlex ID: A5004786699

A StrongREJECT for Empty Jailbreaks

2024 · Alexandra Souly, Qingyuan Lu, et al. · neural information processing systems · 35

PDF

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

2024 · Andriushchenko, Maksym, Souly, Alexandra, et al. · arXiv (Cornell University) · 11

PDF

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

2024 · Alexander Rutherford, Benjamin Ellis, et al. · neural information processing systems · 10

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

2025 · Souly, Alexandra, Rando, Javier, et al. · arXiv (Cornell University) · 8

PDF

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

2023 · Rutherford, Alexander, Ellis, Benjamin, et al. · arXiv (Cornell University) · 4

PDF

Seven simple steps for log analysis in AI systems

2026 · Dubois, Magda, Zorer, Ekin, et al. · arXiv (Cornell University) · 1

PDF

Retrospective on the 2021 BASALT Competition on Learning from Human Feedback

2022 · Shah, Rohin, Wang, Steven H., et al. · arXiv (Cornell University) · 1

PDF

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

UK AISI Alignment Evaluation Case-Study

2026 · Souly, Alexandra, Kirk, Robert, et al. · arXiv (Cornell University)

PDF

Seven simple steps for log analysis in AI systems

2026 · Dubois, Magda, Zorer, Ekin, et al. · Zenodo (CERN European Organization for Nuclear Research)

When Do LLM Preferences Predict Downstream Behavior?

2026 · Slama, Katarina, Souly, Alexandra, et al. · arXiv (Cornell University)

PDF

Seven Steps for Log Analysis Seven Simple Steps for Log Analysis in Ai Systems

2026 · Magda Dubois, Ekin Zorer, et al. · SSRN Electronic Journal

Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs

2025 · Xander Davies, Eric Winsor, et al. · neural information processing systems

PDF

Leading the Pack: N-player Opponent Shaping

2023 · Souly, Alexandra, Willi, Timon, et al. · arXiv (Cornell University)

PDF

Works count: 21

Citation count: 75

H-index: 4

I10-index: 3