PromptCube
Home
AI Models
Prompt Sharing
Workflows
Q&A
Resources
Industry News
AI Coding
AIGC
Members
Search
中
EN
Global AI chat room · 11 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
How Abliteration.AI rewrites model refusals and why it targets security testing
Morgan42
Novice
·
430
·
3
·
12
·
9/3/2026
AI Jailbreak & Security
AI Safety
LLM Security
Astra’s reduced transparency may pose a challenge for jailbreak testing by obscuring its reasoning chain.
AlexTinkerer
Advanced
·
570
·
3
·
3
·
9/3/2026
AI Jailbreak & Security
AI Safety
LLM Security
Stop Prompt Injections with HiveTraceGuard-Pro Qwen3-0.6B
MaxOwl
Intermediate
·
115
·
3
·
15
·
9/2/2026
AI Jailbreak & Security
AI Safety
LLM Security
LLMs Fail to Identify Subtle Social Prejudice Within Complex Group Conversations
AlexGeek
Novice
·
170
·
3
·
9
·
9/2/2026
AI Jailbreak & Security
AI Safety
LLM Security
Researchers uncover how vision-language models bypass safety filters through visual inputs
MaxOwl
Intermediate
·
642
·
4
·
11
·
9/1/2026
AI Jailbreak & Security
AI Safety
LLM Security
AI guardrails are currently failing to solve the fundamental issue.
爱折腾设计师
Intermediate
·
212
·
4
·
7
·
8/31/2026
AI Jailbreak & Security
AI Safety
LLM Security
NeuronFuzz Enhances LLM Safety by Monitoring Internal Neuron Activations During Prefill
JamieWolf
Advanced
·
501
·
4
·
9
·
8/30/2026
AI Jailbreak & Security
AI Safety
LLM Security
Anthropic's new Auto Mode is basically a digital guard that
KaiDev
Expert
·
378
·
3
·
14
·
8/29/2026
AI Jailbreak & Security
AI Safety
LLM Security
Claude Code's Auto Mode Falls Short on Safety Promises
SoloSmith
Expert
·
197
·
3
·
7
·
8/28/2026
AI Jailbreak & Security
AI Safety
LLM Security
Testing Small Language Models for Security Vulnerabilities with BreakBoard
LazyBot
Intermediate
·
655
·
3
·
4
·
8/27/2026
AI Jailbreak & Security
AI Safety
LLM Security
Why the Same-Origin Policy Falls Short for W3C WebMCP Agents
JamieCrafter
Advanced
·
456
·
4
·
3
·
8/26/2026
AI Jailbreak & Security
AI Safety
LLM Security
Advancing LLM Safety Through Multi-Layered Validation Architectures
ChrisCat
Intermediate
·
575
·
3
·
11
·
8/26/2026
AI Jailbreak & Security
AI Safety
LLM Security
Solar eruptions progress through magnetic reconfigurations before releasing charged particles
Max75
Advanced
·
300
·
3
·
3
·
8/25/2026
AI Jailbreak & Security
AI Safety
LLM Security
Subtitle timing can manipulate large vision-language models into bypassing safeguards
JulesTinkerer
Intermediate
·
409
·
4
·
0
·
8/24/2026
AI Jailbreak & Security
AI Safety
LLM Security
Anthropic's IPO acknowledges public AI opposition as a major risk.
CodeSmith
Advanced
·
445
·
4
·
0
·
8/24/2026
AI Jailbreak & Security
AI Safety
LLM Security
1
2
3
4
5
6
7
›
Email
