Picture for Joshua Saxe

Joshua Saxe

Jack

CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models

Add code
Aug 02, 2024
Figure 1 for CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models
Figure 2 for CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models
Figure 3 for CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models
Figure 4 for CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models
Viaarxiv icon

The Llama 3 Herd of Models

Add code
Jul 31, 2024
Viaarxiv icon

CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models

Add code
Apr 19, 2024
Viaarxiv icon

Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

Add code
Dec 07, 2023
Figure 1 for Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models
Figure 2 for Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models
Figure 3 for Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models
Figure 4 for Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models
Viaarxiv icon

A Language-Agnostic Model for Semantic Source Code Labeling

Add code
Jun 03, 2019
Figure 1 for A Language-Agnostic Model for Semantic Source Code Labeling
Figure 2 for A Language-Agnostic Model for Semantic Source Code Labeling
Figure 3 for A Language-Agnostic Model for Semantic Source Code Labeling
Figure 4 for A Language-Agnostic Model for Semantic Source Code Labeling
Viaarxiv icon

A Deep Learning Approach to Fast, Format-Agnostic Detection of Malicious Web Content

Add code
Apr 13, 2018
Figure 1 for A Deep Learning Approach to Fast, Format-Agnostic Detection of Malicious Web Content
Figure 2 for A Deep Learning Approach to Fast, Format-Agnostic Detection of Malicious Web Content
Figure 3 for A Deep Learning Approach to Fast, Format-Agnostic Detection of Malicious Web Content
Figure 4 for A Deep Learning Approach to Fast, Format-Agnostic Detection of Malicious Web Content
Viaarxiv icon

eXpose: A Character-Level Convolutional Neural Network with Embeddings For Detecting Malicious URLs, File Paths and Registry Keys

Add code
Feb 27, 2017
Figure 1 for eXpose: A Character-Level Convolutional Neural Network with Embeddings For Detecting Malicious URLs, File Paths and Registry Keys
Figure 2 for eXpose: A Character-Level Convolutional Neural Network with Embeddings For Detecting Malicious URLs, File Paths and Registry Keys
Figure 3 for eXpose: A Character-Level Convolutional Neural Network with Embeddings For Detecting Malicious URLs, File Paths and Registry Keys
Figure 4 for eXpose: A Character-Level Convolutional Neural Network with Embeddings For Detecting Malicious URLs, File Paths and Registry Keys
Viaarxiv icon