David Wagner

USENIX Security Symposium · 2024

A researcher in the Science corpus: 1 paper; trusts 0 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Papers from David Wagner's perspective

Ordered by how strongly the researchers David Wagner trusts endorse each paper. Same corpus, a different order for every researcher.

  1. Ignore Previous Prompt: Attack Techniques For Language Models
  2. LLaMA: Open and Efficient Foundation Language Models (arXiv.org)
  3. AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
  4. Formalizing and Benchmarking Prompt Injection Attacks and Defenses (USENIX Security Symposium)
  5. The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions (arXiv.org)
  6. Training language models to follow instructions with human feedback (Neural Information Processing Systems)
  7. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
  8. Language Models are Few-Shot Learners (Neural Information Processing Systems)
  9. Attention is All you Need (Neural Information Processing Systems)
  10. Gradient-based learning applied to document recognition

Their papers