NeurIPS 2025 Explorer
Concepts
Authors
Glossary
johnsanterre.github.io
Ivan Evtimov
3 papers
Meta FAIR
AdvPrefix: An Objective for Nuanced LLM Jailbreaks
AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks