Different LLM jailbreak techniques achieve similar harmful compliance but lead to distinct behavioral side effects and mechanistic changes.
Targeted vaccine: Safety alignment for large language models against harmful fine-tuning via layer-wise perturbation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
SAP locates safety-correlated directions via contrastive signals and perturbs hidden-state propagation with a lightweight probe to preserve safety while fine-tuning LLMs for task performance.
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.
citing papers explorer
-
Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks
Different LLM jailbreak techniques achieve similar harmful compliance but lead to distinct behavioral side effects and mechanistic changes.
-
Secure LLM Fine-Tuning via Safety-Aware Probing
SAP locates safety-correlated directions via contrastive signals and perturbs hidden-state propagation with a lightweight probe to preserve safety while fine-tuning LLMs for task performance.
-
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
-
Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.
- Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning