Introduces robust estimators for linear Markov games in offline MARLHF that achieve O(ε^{1-o(1)}) or O(√ε) bounds on Nash or CCE gaps under uniform or unilateral coverage.
Badgpt: Exploring security vulnerabilities of chatgpt via backdoor attacks to instructgpt
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
BadStyle creates stealthy backdoors in LLMs by poisoning samples with imperceptible style triggers and using an auxiliary loss to stabilize payload injection, achieving high attack success rates across multiple models while evading defenses.
Industry AI practitioners view model quality through nine attributes with context-dependent priorities, where data imbalance is a key challenge addressed by strategies like active learning, as confirmed by interviews and a follow-up survey.
Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.
citing papers explorer
-
Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback
Introduces robust estimators for linear Markov games in offline MARLHF that achieve O(ε^{1-o(1)}) or O(√ε) bounds on Nash or CCE gaps under uniform or unilateral coverage.
-
Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
BadStyle creates stealthy backdoors in LLMs by poisoning samples with imperceptible style triggers and using an auxiliary loss to stabilize payload injection, achieving high attack success rates across multiple models while evading defenses.
-
Industry Practitioners Perspectives on AI Model Quality: Perceptions, Challenges, and Solutions
Industry AI practitioners view model quality through nine attributes with context-dependent priorities, where data imbalance is a key challenge addressed by strategies like active learning, as confirmed by interviews and a follow-up survey.
-
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.