Skip to yearly menu bar Skip to main content


(4 events)   Timezone:  
Show all
Toggle Poster Visibility
Oral
Thu Jul 25 07:30 AM -- 07:45 AM (PDT) @ Straus 1-3 None
The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline
In Oral 6E Robustness and Safety
Haonan Wang · Qianli Shen · Yao Tong · Yang Zhang · Kenji Kawaguchi
Oral
Thu Jul 25 07:45 AM -- 08:00 AM (PDT) @ Straus 1-3 None
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
In Oral 6E Robustness and Safety
Christian Schlarmann · Naman Singh · Francesco Croce · Matthias Hein
Oral
Thu Jul 25 08:00 AM -- 08:15 AM (PDT) @ Straus 1-3 None
Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
In Oral 6E Robustness and Safety
Haoran Li · Zicheng Zhang · Wang Luo · Congying Han · Yudong Hu · Tiande Guo · Shichen Liao
[ Slides] 
Oral
Thu Jul 25 08:15 AM -- 08:30 AM (PDT) @ Straus 1-3 None
Scalable AI Safety via Doubly-Efficient Debate
In Oral 6E Robustness and Safety
Jonah Brown-Cohen · Geoffrey Irving · Georgios Piliouras
[ Slides]