usenix security '23 - precise and generalized robustness certification for neural networks
Published 7 months ago • 58 plays • Length 12:19Download video MP4
Download video MP3
Similar videos
-
12:32
usenix security '23 - a data-free backdoor injection approach in neural networks
-
10:17
usenix security '23 - rethinking white-box watermarks on deep learning models under neural...
-
13:45
usenix security '23 - asset: robust backdoor data detection across a multiplicity of deep learning..
-
11:49
usenix security '23 - diffsmooth: certifiably robust learning via diffusion models and local...
-
13:15
usenix security '23 - airs: explanation for deep reinforcement learning based security applications
-
9:34
usenix security '23 - icspatch: automated vulnerability localization and non-intrusive...
-
12:34
usenix security '23 - uret: universal robustness evaluation toolkit (for evasion)
-
17:51
ndss 2023 - bars: local robustness certification for deep learning based traffic analysis systems
-
37:46
privacy preserving machine learning over encrypted data
-
24:49
generative ai in cybersecurity: rise of the machines?
-
12:04
usenix security '23 - not all data are created equal: data and pointer prioritization for scalable..
-
12:47
usenix security '23 - aliasing backdoor attacks on pre-trained models
-
13:09
usenix security '23 - can a deep learning model for one architecture be used for others?...
-
14:56
sok: certified robustness for deep neural networks
-
11:16
usenix security '23 - a hybrid alias analysis and its application to global variable protection...
-
10:58
usenix security '20 - high accuracy and high fidelity extraction of neural networks
-
10:05
usenix security '22 - cheetah: lean and fast secure two-party deep neural network inference
-
26:51
usenix security '18 - gazelle: a low latency framework for secure neural network inference
-
26:23
usenix security '15 - recognizing functions in binaries with neural networks
-
14:41
usenix security '23 - a research framework and initial study of browser security for the visually...