Download video

USENIX Security '23 - CodexLeaks: Privacy Leaks from Code Generation Language Models in GitHub...

85 views

USENIX

1 year ago

USENIX Security '23 - CodexLeaks: Privacy Leaks from Code Generation Language Models in GitHub...

USENIX Security '23 - CodexLeaks: Privacy Leaks from Code Generation Language Models in GitHub...

USENIX Security '23 - Can a Deep Learning Model for One Architecture Be Used for Others?...
13:09
USENIX Security '23 - Can a Deep Learning Model for One Architecture Be Used for Others?...
by USENIX
USENIX Security '23 - Pass2Edit: A Multi-Step Generative Model for Guessing Edited Passwords
11:19
USENIX Security '23 - Pass2Edit: A Multi-Step Generative Model for Guessing Edited Passwords
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 '23 - The Space of Adversarial Strategies
11:48
USENIX Security '23 - The Space of Adversarial Strategies
by USENIX
USENIX Security '23 - Beyond Typosquatting: An In-depth Look at Package Confusion
11:35
USENIX Security '23 - Beyond Typosquatting: An In-depth Look at Package Confusion
by USENIX
USENIX Security '23 - Aliasing Backdoor Attacks on Pre-trained Models
12:47
USENIX Security '23 - Aliasing Backdoor Attacks on Pre-trained Models
by USENIX
USENIX Security '23 - PUMM: Preventing Use-After-Free Using Execution Unit Partitioning
9:20
USENIX Security '23 - PUMM: Preventing Use-After-Free Using Execution Unit Partitioning
by USENIX
USENIX Security '23 - A Peek into the Metaverse: Detecting 3D Model Clones in Mobile Games
12:15
USENIX Security '23 - A Peek into the Metaverse: Detecting 3D Model Clones in Mobile Games
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
AI Safety - Computerphile
6:03
AI Safety - Computerphile
by Computerphile
Brendan McMahan - Guarding user Privacy with Federated Learning and Differential Privacy
31:30
Brendan McMahan - Guarding user Privacy with Federated Learning and Differential Privacy
by DIMACS CCICADA
USENIX Security '21 - Too Good to Be Safe: Tricking Lane Detection in Autonomous Driving with Craft
11:48
USENIX Security '21 - Too Good to Be Safe: Tricking Lane Detection in Autonomous Driving with Craft
by USENIX
USENIX Security '23 - Two-in-One: A Model Hijacking Attack Against Text Generation Models
13:16
USENIX Security '23 - Two-in-One: A Model Hijacking Attack Against Text Generation Models
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
USENIX Security '23 - Rethinking White-Box Watermarks on Deep Learning Models under Neural...
10:17
USENIX Security '23 - Rethinking White-Box Watermarks on Deep Learning Models under Neural...
by USENIX
USENIX Security '22 - FLAME: Taming Backdoors in Federated Learning
10:20
USENIX Security '22 - FLAME: Taming Backdoors in Federated Learning
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 '23 - Speculation at Fault: Modeling and Testing Microarchitectural Leakage of...
11:20
USENIX Security '23 - Speculation at Fault: Modeling and Testing Microarchitectural Leakage of...
by USENIX
USENIX Security '24 - SoK: All You Need to Know About On-Device ML Model Extraction - The Gap...
9:41
USENIX Security '24 - SoK: All You Need to Know About On-Device ML Model Extraction - The Gap...
by USENIX
USENIX Security '24 - Double Face: Leveraging User Intelligence to Characterize and Recognize...
12:30
USENIX Security '24 - Double Face: Leveraging User Intelligence to Characterize and Recognize...
by USENIX
USENIX Security '24 - An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models:...
11:16
USENIX Security '24 - An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models:...
by USENIX
USENIX Security '23 - Capstone: A Capability-based Foundation for Trustless Secure Memory Access
12:41
USENIX Security '23 - Capstone: A Capability-based Foundation for Trustless Secure Memory Access
by USENIX
USENIX Security '23 - Evading Provenance-Based ML Detectors with Adversarial System Action
13:59
USENIX Security '23 - Evading Provenance-Based ML Detectors with Adversarial System Action
by USENIX