Author

Maksym Andriushchenko

Observed name: Andriushchenko, Maksym

Institutions: Max Planck Institute for Intelligent Systems, Tübingen AI Center, ELLIS Institute Tübingen

Observed institutions: University of Oxford, Max Planck Institute for Intelligent Systems, Tübingen AI Center, ELLIS Institute Tübingen, École Polytechnique Fédérale de Lausanne

OpenAlex ID: A5120034502

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

2026 · Schmotz, David, Beurer-Kellner, Luca, et al. · arXiv (Cornell University) · 109

PDF

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

2025 · Thomas Kuntz, Agatha Duzan, et al. · neural information processing systems · 95

PDF

PostTrainBench: Can LLM Agents Automate LLM Post-Training?

2026 · Rank, Ben, Bhatnagar, Hardik, et al. · arXiv (Cornell University) · 78

PDF

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

2025 · Terekhov, Mikhail, Panfilov, Alexander, et al. · arXiv (Cornell University) · 40

PDF

Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors

2025 · Yueh-Han, Chen, Joshi, Nitish, et al. · arXiv (Cornell University) · 27

PDF

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

2026 · Panfilov, Alexander, Romov, Peter, et al. · arXiv (Cornell University) · 23

PDF

International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications

2025 · Bengio, Yoshua, Clare, Stephen, et al. · arXiv (Cornell University) · 15

PDF

HalluHard: A Hard Multi-Turn Hallucination Benchmark

2026 · Fan, Dongyang, Delsad, Sebastien, et al. · arXiv (Cornell University) · 13

PDF

International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management

2025 · Yoshua Bengio, Stephen Clare, et al. · SuperIntelligence - Robotics - Safety & Alignment · 11

PDF

FutureSim: Replaying World Events to Evaluate Adaptive Agents

2026 · Goel, Shashwat, Chandak, Nikhil, et al. · arXiv (Cornell University) · 10

PDF

ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D

2026 · Libon, Lena, Rank, Ben, et al. · arXiv (Cornell University) · 8

PDF

Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors

2026 · Wiedermann-Möller, Jonas, Dung, Leonard, et al. · arXiv (Cornell University) · 3

PDF

Characterizing the Consistency of the Emergent Misalignment Persona

2026 · Weckauff, Anietta, Zhang, Yuchen, et al. · arXiv (Cornell University) · 1

PDF

International Al Safety Report: First Key Update Capabilities and Risk Implications

2025 · Yoshua Bengio, Benjamin Bucknall, et al. · SuperIntelligence - Robotics - Safety & Alignment · 1

PDF

What Shapes Emergent Misalignment? Insights from Training Dynamics, Model Priors, and Data

2026 · Zhang, Yuchen, Weckauff, Anietta, et al. · arXiv (Cornell University)

PDF

Europe and the Geopolitics of AGI: The Need for a Preparedness Plan

2026 · Negele, Maximilian, Juijn, Daan, et al. · arXiv (Cornell University)

PDF

Works count: 16

Citation count: 434

H-index: 10

I10-index: 10