▲

0

▼

Premium: Jailbreaks Premium

Automated attacks outperform manual

Automated attacks outperform manual

By Zhang et al. Oct 22, 2025

GPT-3 Manual-vs-Auto

▲

0

▼

Premium: Jailbreaks Premium

Preamble's early gpt-3 discovery - may 2022

Preamble's early GPT-3 discovery - May 2022

By Preamble Inc. Oct 22, 2025

GPT-3 Historical

▲

0

▼

Premium: Jailbreaks Premium

Automated jailbreak fuzzing

Automated jailbreak fuzzing

By Yu et al. Oct 22, 2025

GPT-3 GPTFuzzer Jailbreak

▲

-1

▼

Premium: Jailbreaks Premium

Viral sept 2022 translation injection

Viral Sept 2022 translation injection

By Riley Goodside Oct 22, 2025

GPT-3 Translation-Attack

▲

-1

▼

Premium: Jailbreaks Premium

Attacking cloze vs prefix prompts

Attacking cloze vs prefix prompts

By Research Oct 22, 2025

Cloze-Prompt-Attack GPT-3

▲

-1

▼

Premium: Jailbreaks Premium

Evading perplexity-based filters

Evading perplexity-based filters

By Research Oct 22, 2025

GPT-3 Perplexity-Evasion

▲

-1

▼

Premium: Jailbreaks Premium

Automated prompt leaking attack

Automated prompt leaking attack

By Hui et al. Oct 22, 2025

GPT-3 LLaMA PLeak-Method

▲

-1

▼

Premium: Jailbreaks Premium

Promptinject kaleidoscopic variations

PromptInject kaleidoscopic variations

By Research Oct 22, 2025

GPT-3 Secret-Subprompt

▲

-1

▼

Premium: Jailbreaks Premium

Dos attack - model outputs no text

DoS attack - model outputs no text

By Research Oct 22, 2025

Denial-of-Service GPT-3

▲

-1

▼

Premium: Jailbreaks Premium

Delimiter bypass improves attack by 40%

Delimiter bypass improves attack by 40%

By Perez & Ribeiro Oct 22, 2025

Delimiter-Weakness GPT-3

▲

-1

▼

Premium: Jailbreaks Premium

Named 'prompt injection' sept 2022

Named 'prompt injection' Sept 2022

By Simon Willison Oct 22, 2025

GPT-3 String-Concat

▲

-1

▼

Premium: Jailbreaks Premium

Exploiting prefix prompt architecture

Exploiting prefix prompt architecture

By Research Oct 22, 2025

GPT-3 Prefix-Prompt-Attack