TE
TechEcho
Home
24h Top
Newest
Best
Ask
Show
Jobs
English
GitHub
Twitter
Back to Profile
Submissions by rhavaei
1
A comprehensive analysis of Llama4 safety in CBRN tasks vs. closed-source models [pdf]
2 points
by
rhavaei
25 days ago
no comments
2
LLM Robustness/Safety Benchmark
2 points
by
rhavaei
about 1 month ago
no comments
3
An Implementation of AutoDAN Turbo
2 points
by
rhavaei
about 2 months ago
no comments
4
Using Deepseek R1 to Break LLMs: Tree of Attacks
7 points
by
rhavaei
about 2 months ago
no comments
5
The Jailbreak Bible
17 points
by
rhavaei
about 2 months ago
4 comments
6
Red-Teaming ChatGPT for Hallucinations – Code and Report
1 points
by
rhavaei
3 months ago
no comments
7
Consistent Jailbreaking Method in o1, o3, and 4o
8 points
by
rhavaei
3 months ago
17 comments
8
Jailbroken: Finding 50,000 Legal Hallucinations in GPT-4o with RL
4 points
by
rhavaei
4 months ago
2 comments
← Previous
Next →