PromptCube
Home
AI Models
Prompt Sharing
Workflows
Q&A
Resources
Industry News
AI Coding
AIGC
Members
Search
中
EN
Global AI chat room · 12 online now
Join now
Home
/
AI Jailbreak & Security
AI Jailbreak & Security
95 posts
Safety research only. No attack recipes.
Sort:
Latest
Hot
Most Replies
AI Jailbreak & Security — All Posts
Can Item Response Theory fix LLM safety evaluation for good?
AlexHacker
Expert
·
120
·
3
·
5
·
8/9/2026
AI Jailbreak & Security
AI Safety
LLM Security
PIMiner’s agentic approach outperforms static methods on Gemini‑2.5‑Pro and other models
NovaOwl
Intermediate
·
592
·
4
·
13
·
8/8/2026
AI Jailbreak & Security
AI Safety
LLM Security
Multimodal LLMs with full tool access risk turning TV ads into dangerous commands
产品经理大熊
Advanced
·
457
·
3
·
14
·
8/8/2026
AI Jailbreak & Security
AI Safety
LLM Security
LLMs reject prompts based on sentence structure more than actual harmful intent.
NovaGuru
Advanced
·
469
·
4
·
11
·
8/7/2026
AI Jailbreak & Security
AI Safety
LLM Security
Why AI safeguards are just prompts—and how to bypass them
DeepWhiz
Intermediate
·
231
·
4
·
13
·
8/7/2026
AI Jailbreak & Security
AI Safety
LLM Security
Longer conversation history in LLMs worsens delusional response patterns, study finds
Leo37
Novice
·
513
·
3
·
15
·
8/6/2026
AI Jailbreak & Security
AI Safety
LLM Security
Claude Opus alignment shatters under a three-word prompt logic
Alex17
Advanced
·
352
·
4
·
8
·
8/6/2026
AI Jailbreak & Security
AI Safety
LLM Security
Classroom interactions expose how large language models fail under realistic teaching scenarios
Riley2
Advanced
·
454
·
4
·
15
·
8/5/2026
AI Jailbreak & Security
AI Safety
LLM Security
Frontier AI labs’ conflicting letters reveal clashing visions for safety and speed
Drew15
Expert
·
264
·
3
·
9
·
8/5/2026
AI Jailbreak & Security
AI Safety
LLM Security
LiteLLM Gateway Hijacking Highlights Critical Risks for AI Infrastructure
爱折腾设计师
Intermediate
·
190
·
3
·
4
·
8/4/2026
AI Jailbreak & Security
AI Safety
LLM Security
Jackpot Lab: 10 Broken LLM Apps You Can Poke at in Your Browser
自由职业运营喵
Advanced
·
116
·
3
·
2
·
8/4/2026
AI Jailbreak & Security
AI Safety
LLM Security
Agentic Supply Chains: The Overlooked OWASP Risk That Threatens My Sleep
DrewWizard
Intermediate
·
226
·
3
·
5
·
7/31/2026
AI Jailbreak & Security
AI Safety
LLM Security
Hugging Face Security Analysis Details An OpenAI Agent Sandbox Escape Incident
Riley97
Advanced
·
390
·
4
·
15
·
7/30/2026
AI Jailbreak & Security
AI Safety
LLM Security
Hacker Holidays 2026’s Concierge Knows Too Much exposes why system prompts fail as security
JulesCrafter
Novice
·
406
·
3
·
9
·
7/29/2026
AI Jailbreak & Security
AI Safety
LLM Security
Mask2Shield: How Redistributing Safety Logic Across the LLM Network Thwarts Pruning Attacks
GhostOwl
Intermediate
·
226
·
4
·
15
·
7/28/2026
AI Jailbreak & Security
AI Safety
LLM Security
‹
1
2
3
4
5
6
7
›
Email
