Download video

USENIX Security '24 - Towards More Practical Threat Models in Artificial Intelligence Security

45 views

USENIX

6 months ago

USENIX Security '24 - Towards More Practical Threat Models in Artificial Intelligence Security

USENIX Security '24 - Towards More Practical Threat Models in Artificial Intelligence Security

USENIX Security '24 - Splitting the Difference on Adversarial Training
12:31
USENIX Security '24 - Splitting the Difference on Adversarial Training
by USENIX
USENIX Security '24 - Reconstructing training data from document understanding models
10:38
USENIX Security '24 - Reconstructing training data from document understanding models
by USENIX
USENIX Security '24 - BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in...
17:39
USENIX Security '24 - BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in...
by USENIX
USENIX Security '24 - PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation...
10:23
USENIX Security '24 - PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation...
by USENIX
USENIX Security '22 - On the Security Risks of AutoML
10:16
USENIX Security '22 - On the Security Risks of AutoML
by USENIX
USENIX Security '23 - DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local...
11:49
USENIX Security '23 - DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local...
by USENIX
USENIX Security '24 - SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models
11:42
USENIX Security '24 - SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models
by USENIX
Nextgen Software and Awakeness.ai @ #BCC2024
3:42
Nextgen Software and Awakeness.ai @ #BCC2024
by CyberSecTV
USENIX Security '24 - AI Psychiatry: Forensic Investigation of Deep Learning Networks in Memory...
9:15
USENIX Security '24 - AI Psychiatry: Forensic Investigation of Deep Learning Networks in Memory...
by USENIX
USENIX Security '21 - PrivSyn: Differentially Private Data Synthesis
11:35
USENIX Security '21 - PrivSyn: Differentially Private Data Synthesis
by USENIX
L FGADMM Layer-wise Federated Group ADMM
14:37
L FGADMM Layer-wise Federated Group ADMM
by Intelligent Connectivity and Networks
NAE Grand Challenge: Reverse Engineering the Brain by Visualizing Neural Networks
10:23
NAE Grand Challenge: Reverse Engineering the Brain by Visualizing Neural Networks
by lgdragon040
USENIX Security '24 - SoK: Neural Network Extraction Through Physical Side Channels
12:57
USENIX Security '24 - SoK: Neural Network Extraction Through Physical Side Channels
by USENIX
USENIX Security '23 - PELICAN: Exploiting Backdoors of Naturally Trained Deep Learning Models In...
11:57
USENIX Security '23 - PELICAN: Exploiting Backdoors of Naturally Trained Deep Learning Models In...
by USENIX
USENIX Security '24 - Improving ML-based Binary Function Similarity Detection by Assessing and...
11:02
USENIX Security '24 - Improving ML-based Binary Function Similarity Detection by Assessing and...
by USENIX
USENIX ATC '24 - Centimani: Enabling Fast AI Accelerator Selection for DNN Training with a Novel...
22:11
USENIX ATC '24 - Centimani: Enabling Fast AI Accelerator Selection for DNN Training with a Novel...
by USENIX
WOOT '24 - Lightning Talk: AI Cyber Challenge
5:11
WOOT '24 - Lightning Talk: AI Cyber Challenge
by USENIX
USENIX Security '23 - The Space of Adversarial Strategies
11:48
USENIX Security '23 - The Space of Adversarial Strategies
by USENIX
USENIX Security '24 - Making Them Ask and Answer: Jailbreaking Large Language Models in Few...
14:07
USENIX Security '24 - Making Them Ask and Answer: Jailbreaking Large Language Models in Few...
by USENIX
USENIX Security '20 - Exploring Connections Between Active Learning and Model Extraction
10:28
USENIX Security '20 - Exploring Connections Between Active Learning and Model Extraction
by USENIX
Problemlösung für nicht angezeigte YouTube-Bibliotheksoptionen (2025)
2:01
Problemlösung für nicht angezeigte YouTube-Bibliotheksoptionen (2025)
by Solution All Active
USENIX Security '24 - Formal verification of the PQXDH Post-Quantum key agreement protocol for...
14:37
USENIX Security '24 - Formal verification of the PQXDH Post-Quantum key agreement protocol for...
by USENIX
USENIX Security '23 - CodexLeaks: Privacy Leaks from Code Generation Language Models in GitHub...
11:47
USENIX Security '23 - CodexLeaks: Privacy Leaks from Code Generation Language Models in GitHub...
by USENIX