Jeff Sims’ Post

View profile for Jeff Sims

Senior Staff Data Scientist | CBRN Red Team | BlackMamba | Red Reaper | EyeSpy Author

RAG Poisoning (PANDORA) – found something cool in the knowledge graph this am: “The integration of various plugins into LLMs, notably Retrieval Augmented Generation (RAG), which enables LLMs to incorporate external knowledge bases into their response generation such as GPTs, introduces new avenues for indirect jailbreak attacks. To fill this gap, we investigate indirect jailbreak attacks on LLMs, particularly GPTs, introducing a novel attack vector named Retrieval Augmented Generation Poisoning. This method, PANDORA, exploits the synergy between LLMs and RAG through prompt manipulation to generate unexpected responses. PANDORA uses maliciously crafted content to influence the RAG process, effectively initiating jailbreak attacks.” Paper: https://lnkd.in/eFXUwQtH #malware, #ai, #informationsecurity, #blueteam #reverseengineering #cyberdefense #cybercrime, #cyberthreatintelligence, #cyberdefense, #cyberwarfare #networksecurity #sec #security #tools #offensivesecurity, #redteam #innovation

  • chart, bubble chart
Wesley Swann

M365 Enterprise Expert • Azure Architect • Mentor • C|EI • C|EH • C|EH TOP 100 • C|HFI • C|ND • C|NDA • C|CSE • CRISC • CCSK • MCSE • MCSA • Intune • M365 & Azure Security • Endpoint • IAM

8mo

Fascinating insights on indirect jailbreak attacks in LLMs. Can't wait to check out the paper. 🔒

Andria Delia

Cyber Threat Intelligence Expert~ International Speaker ~ Named “Tech Visionary” ~ Ransomware Mitigation & Incident Response/Pentest/Breach Analysis/Forensics/Risk & Compliance/IT Security/Litigation Support/DefensiveTTP

8mo

Very informative

Ammar Hakim Haris

Cyber Security Architect & Governance Risk Assessment Complaince

8mo

Good Point

Like
Reply
See more comments

To view or add a comment, sign in

Explore topics