all AI news
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
April 29, 2024, 4:42 a.m. | Anselm Paulus, Arman Zharmagambetov, Chuan Guo, Brandon Amos, Yuandong Tian
cs.LG updates on arXiv.org arxiv.org
Abstract: While recently Large Language Models (LLMs) have achieved remarkable successes, they are vulnerable to certain jailbreaking attacks that lead to generation of inappropriate or harmful content. Manual red-teaming requires finding adversarial prompts that cause such jailbreaking, e.g. by appending a suffix to a given instruction, which is inefficient and time-consuming. On the other hand, automatic adversarial prompt generation often leads to semantically meaningless attacks that can easily be detected by perplexity-based filters, may require gradient …
abstract adversarial arxiv attacks cs.ai cs.cl cs.cr cs.lg inappropriate jailbreaking language language models large language large language models llms prompting prompts type vulnerable while
More from arxiv.org / cs.LG updates on arXiv.org
Testing the Segment Anything Model on radiology data
1 day, 15 hours ago |
arxiv.org
Calorimeter shower superresolution
1 day, 15 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US