Research Publications
Research Publication
Steering Vectors are an Adversarial Attack Surface
arXiv (Cornell University)Jun 4, 20260 OpenAlex citationsMatched to OpenAlex
DOI: 10.48550/arxiv.2606.05958
Publication summary
Matched to OpenAlexNo abstract is available yet. The publication is shown because it is linked to an approved public researcher profile.
Adversarial Robustness in Machine LearningTopic ModelingSecurity and Verification in Computingactivation steeringlarge language modelsadversarial attacksjailbreakingrefusal behavior
Authors
Related publications
Connected through authors and topics already present in the Research Hub.
AICD Bench: A Challenging Benchmark for AI-Generated Code DetectionTUbilio (Technical University of Darmstadt) · 2026 · 0 OpenAlex citationsShared topic: Adversarial Robustness in Machine LearningTransliteration for Low-Resource Translation in the Age of Large Language ModelsElectronics · 2026 · 0 OpenAlex citationsShared topic: Topic ModelingByzantine-Robust Optimization under $(L_0, L_1)$-SmoothnessarXiv (Cornell University) · 2026 · 0 OpenAlex citationsShared topic: Adversarial Robustness in Machine LearningArchitecting the Orthopedical Clinical AI Pipeline: A Review of Integrating Foundation Models and FHIR for Agentic Clinical Assistants and Digital TwinsAlgorithms · 2026 · 0 OpenAlex citationsShared topic: Topic Modeling