Chawin Sitawarin
@chawins.bsky.social
Postdoc @Meta (Privacy-Preserving ML | Central Applied Science). PhD CS @UCBerkeley. ML security 👹 privacy 👀 robustness 🛡 Views are my own.
Pinned
Chawin Sitawarin
@chawins.bsky.social
· Dec 12
📢 Excited to share our new result on LLM jailbreak!
⚔️ We propose IRIS, a simple automated 𝘂𝗻𝗶𝘃𝗲𝗿𝘀𝗮𝗹 𝗮𝗻𝗱 𝘁𝗿𝗮𝗻𝘀𝗳𝗲𝗿𝗿𝗮𝗯𝗹𝗲 𝗷𝗮𝗶𝗹𝗯𝗿𝗲𝗮𝗸 𝘀𝘂𝗳𝗳𝗶𝘅 that works on GPTs, o1, and Circuit Breaker defense! To appear at NeurIPS Safe GenAI Workshop!
(1/7)
⚔️ We propose IRIS, a simple automated 𝘂𝗻𝗶𝘃𝗲𝗿𝘀𝗮𝗹 𝗮𝗻𝗱 𝘁𝗿𝗮𝗻𝘀𝗳𝗲𝗿𝗿𝗮𝗯𝗹𝗲 𝗷𝗮𝗶𝗹𝗯𝗿𝗲𝗮𝗸 𝘀𝘂𝗳𝗳𝗶𝘅 that works on GPTs, o1, and Circuit Breaker defense! To appear at NeurIPS Safe GenAI Workshop!
(1/7)
📢 Excited to share our new result on LLM jailbreak!
⚔️ We propose IRIS, a simple automated 𝘂𝗻𝗶𝘃𝗲𝗿𝘀𝗮𝗹 𝗮𝗻𝗱 𝘁𝗿𝗮𝗻𝘀𝗳𝗲𝗿𝗿𝗮𝗯𝗹𝗲 𝗷𝗮𝗶𝗹𝗯𝗿𝗲𝗮𝗸 𝘀𝘂𝗳𝗳𝗶𝘅 that works on GPTs, o1, and Circuit Breaker defense! To appear at NeurIPS Safe GenAI Workshop!
(1/7)
⚔️ We propose IRIS, a simple automated 𝘂𝗻𝗶𝘃𝗲𝗿𝘀𝗮𝗹 𝗮𝗻𝗱 𝘁𝗿𝗮𝗻𝘀𝗳𝗲𝗿𝗿𝗮𝗯𝗹𝗲 𝗷𝗮𝗶𝗹𝗯𝗿𝗲𝗮𝗸 𝘀𝘂𝗳𝗳𝗶𝘅 that works on GPTs, o1, and Circuit Breaker defense! To appear at NeurIPS Safe GenAI Workshop!
(1/7)
December 12, 2024 at 6:16 PM
📢 Excited to share our new result on LLM jailbreak!
⚔️ We propose IRIS, a simple automated 𝘂𝗻𝗶𝘃𝗲𝗿𝘀𝗮𝗹 𝗮𝗻𝗱 𝘁𝗿𝗮𝗻𝘀𝗳𝗲𝗿𝗿𝗮𝗯𝗹𝗲 𝗷𝗮𝗶𝗹𝗯𝗿𝗲𝗮𝗸 𝘀𝘂𝗳𝗳𝗶𝘅 that works on GPTs, o1, and Circuit Breaker defense! To appear at NeurIPS Safe GenAI Workshop!
(1/7)
⚔️ We propose IRIS, a simple automated 𝘂𝗻𝗶𝘃𝗲𝗿𝘀𝗮𝗹 𝗮𝗻𝗱 𝘁𝗿𝗮𝗻𝘀𝗳𝗲𝗿𝗿𝗮𝗯𝗹𝗲 𝗷𝗮𝗶𝗹𝗯𝗿𝗲𝗮𝗸 𝘀𝘂𝗳𝗳𝗶𝘅 that works on GPTs, o1, and Circuit Breaker defense! To appear at NeurIPS Safe GenAI Workshop!
(1/7)