all InfoSec news
Backdoor Removal for Generative Large Language Models
May 14, 2024, 4:11 a.m. | Haoran Li, Yulin Chen, Zihao Zheng, Qi Hu, Chunkit Chan, Heshan Liu, Yangqiu Song
cs.CR updates on arXiv.org arxiv.org
Abstract: With rapid advances, generative large language models (LLMs) dominate various Natural Language Processing (NLP) tasks from understanding to reasoning. Yet, language models' inherent vulnerabilities may be exacerbated due to increased accessibility and unrestricted model training on massive textual data from the Internet. A malicious adversary may publish poisoned data online and conduct backdoor attacks on the victim LLMs pre-trained on the poisoned data. Backdoored LLMs behave innocuously for normal queries and generate harmful responses when …
accessibility adversary arxiv backdoor cs.cl cs.cr data generative internet language language models large llms malicious may model training natural natural language natural language processing nlp rapid reasoning training understanding vulnerabilities
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
CyberSOC Technical Lead
@ Integrity360 | Sandyford, Dublin, Ireland
Cyber Security Strategy Consultant
@ Capco | New York City
Cyber Security Senior Consultant
@ Capco | Chicago, IL
Sr. Product Manager
@ MixMode | Remote, US
Corporate Intern - Information Security (Year Round)
@ Associated Bank | US WI Remote
Senior Offensive Security Engineer
@ CoStar Group | US-DC Washington, DC