conftrace_

model safeguard

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

jailbreak tuning (1) open-weight model (1) large language model (1) copyright infringement (1) adversarial prompting (1) persuasion technique (1) model customization (1) content generation (1) fine-tuning attack (1) safety evaluation (1)

Papers

Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility EMNLP 2025 On Evaluating the Durability of Safeguards for Open-Weight LLMs ICLR 2025 Profiling LLM’s Copyright Infringement Risks under Adversarial Persuasive Prompting EMNLP 2025