April 4, 2024, 4:47 a.m. | Victoria Graf, Qin Liu, Muhao Chen

cs.CL updates on arXiv.org arxiv.org

arXiv:2404.02356v1 Announce Type: new
Abstract: Data poisoning backdoor attacks can cause undesirable behaviors in large language models (LLMs), and defending against them is of increasing importance. Existing defense mechanisms often assume that only one type of trigger is adopted by the attacker, while defending against multiple simultaneous and independent trigger types necessitates general defense frameworks and is relatively unexplored. In this paper, we propose Nested Product of Experts(NPoE) defense framework, which involves a mixture of experts (MoE) as a trigger-only …

abstract arxiv attacks backdoor cs.cl data data poisoning defense importance language language models large language large language models llms multiple poe robust them type

Data Scientist (m/f/x/d)

@ Symanto Research GmbH & Co. KG | Spain, Germany

Data Analyst, Client Insights and Analytics - New Graduate, Full Time

@ Scotiabank | Toronto, ON, CA

Consultant Senior Data Scientist (H/F)

@ Publicis Groupe | Paris, France

Data Analyst H/F - CDI

@ Octapharma | Lingolsheim, FR

Lead AI Engineer

@ Ford Motor Company | United States

Senior Staff Machine Learning Engineer

@ Warner Bros. Discovery | CA San Francisco 153 Kearny Street