Skip to yearly menu bar Skip to main content


(4 events)   Timezone:  
Show all
Toggle Poster Visibility
Oral
Tue Jul 07 06:00 PM -- 06:15 PM (PDT) @ AUDITORIUM None
Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
In Oral 3F AI Safety & Jailbreaks
Zhicheng Fang ⋅ Jingjie Zheng ⋅ Chenxu Fu ⋅ Wei Xu
[ Slides]  [ OpenReview] 
Oral
Tue Jul 07 06:15 PM -- 06:30 PM (PDT) @ AUDITORIUM None
Quantifying Frontier LLM Capabilities for Container Sandbox Escape
In Oral 3F AI Safety & Jailbreaks
Rahul Marchand ⋅ Art Cathain ⋅ Jerome Wynne ⋅ Philippos Giavridis ⋅ Sam Deverett ⋅ John Wilkinson ⋅ Jason Gwartz ⋅ Harry Coppock
[ OpenReview] 
Oral
Tue Jul 07 06:30 PM -- 06:45 PM (PDT) @ AUDITORIUM None
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models
In Oral 3F AI Safety & Jailbreaks
Yanchen Yin ⋅ Dongqi Han ⋅ Linghui Li
[ OpenReview] 
Oral
Tue Jul 07 06:45 PM -- 07:00 PM (PDT) @ AUDITORIUM None
When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
In Oral 3F AI Safety & Jailbreaks
Jiacheng Hou ⋅ Yining Sun ⋅ Ruochong Jin ⋅ Haochen Han ⋅ Fangming Liu ⋅ Victor Chan ⋅ Alex Jinpeng Wang
[ OpenReview]