usenix security '23 - two-in-one: a model hijacking attack against text generation models
Published 9 months ago • 66 plays • Length 13:16Download video MP4
Download video MP3
Similar videos
-
13:09
usenix security '23 - can a deep learning model for one architecture be used for others?...
-
12:11
usenix security '23 - jinn: hijacking safe programs with trojans
-
12:55
usenix security '23 - that person moves like a car: misclassification attack detection fo...
-
9:34
usenix security '23 - icspatch: automated vulnerability localization and non-intrusive...
-
13:39
usenix security '23 - person re-identification in 3d space: a wifi vision-based approach
-
10:28
usenix security '20 - exploring connections between active learning and model extraction
-
17:53
usenix security '23 - detecting and handling iot interaction threats in multi-platform multi...
-
12:55
usenix security '23 - sneaky spy devices and defective detectors: the ecosystem of intimate...
-
6:38
aitm attack demo
-
10:49
usenix security '23 - remote direct memory introspection
-
14:15
ndss 2022 get a model! model hijacking attack against machine learning models
-
10:51
usenix security '23 - design of access control mechanisms in systems-on-chip with formal...
-
15:26
usenix security '23 - humans vs. machines in malware classification
-
12:51
usenix security '23 - automata-guided control-flow-sensitive fuzz driver generation
-
11:06
usenix security '22 - label inference attacks against vertical federated learning
-
14:53
usenix security '23 - csher: a system for compact storage with he-retrieval
-
11:12
usenix security '22 - frameshifter: security implications of http/2-to-http/1 conversion anomalies
-
12:29
usenix security '23 - adversarial training for raw-binary malware classifiers
-
12:04
usenix security '23 - detecting multi-step iam attacks in aws environments via model checking
-
11:48
usenix security '23 - horuseye: a realtime iot malicious traffic detection framework using...
-
11:07
usenix security '21 - hermes attack: steal dnn models with lossless inference accuracy