Skip to content
conftrace_

robust alignment

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (3) harmful fine-tuning (1) embedding drift (1) human preference (1) llm safety (1) alignment training (1) adversarial fine-tuning (1) embedding perturbation (1) alignment-breaking attack (1) jailbreaking prompt (1)

Papers

Hierarchically Robust Zero-shot Vision-language Models CVPR 2026 Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM ACL 2024 Perplexity-aware Correction for Robust Alignment with Noisy Preferences NeurIPS 2024 Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack NeurIPS 2024