New #J2C Certification:
Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective
Sahil Verma, Gantavya Bhatt, Avi Schwarzschild et al.
https://openreview.net/forum?id=Conma3qnaT
#adversarial #backdooring #backdoors
Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective
Sahil Verma, Gantavya Bhatt, Avi Schwarzschild et al.
Action editor: Yingzhen Li
https://openreview.net/forum?id=Conma3qnaT
#adversarial #backdooring #backdoors
Stealthy Backdoor Attack via Confidence-driven Sampling
Pengfei He, Yue Xing, Han Xu et al.
Action editor: Stanislaw Jastrzebski
https://openreview.net/forum?id=Flh5EXz8dA
#backdooring #attacks #backdoor
