Alerts
Events
DCR
Explore Cyware Products
Alerts
Events
DCR
Go to listing page
Researchers Automated Jailbreaking of LLMs With Other LLMs
Innovation and Research
December 09, 2023
Help Net Security
Researchers have developed an automated machine learning technique, called TAP, that can quickly exploit vulnerabilities in large language models (LLMs) and make them produce harmful and toxic responses.
Read More
Tree of Attacks with Pruning (TAP)
Large Language Model (LLM)
Jailbreaking
AI Models
Security Weaknesses
Publisher
Previous
HHS Announces Next Steps in Ongoing Work to Enhance Cyb ...
Strategy and Planning
Next
Bypassing Major EDRs Using Pool Party Process Injection ...
Malware and Vulnerabilities