REDEEM MYSELF: Purifying Backdoors in Deep Learning Models using Self Attention Distillation

Name: REDEEM MYSELF: Purifying Backdoors in Deep Learning Models using Self Attention Distillation
Uploaded: 2023-01-01
Duration: 14 min 42 s
Description: REDEEM MYSELF: Purifying Backdoors in Deep Learning Models using Self Attention Distillation — a 2023 IEEE S&P 2023 Sessions security conference talk on ai-ml (14:42 min). Watch the full video, indexed free on the Breach Arc Archive.

IEEE S&P 2023 Sessions · 2023 · 14:42

▶

REDEEM MYSELF: Purifying Backdoors in Deep Learning Models using Self Attention Distillation — a 2023 IEEE S&P 2023 Sessions security conference talk on ai-ml (14:42 min). Watch the full video, indexed free on the Breach Arc Archive.

▶ Watch video on YouTube

ai-ml

← Back to the Breach Arc Archive