AI Jailbreak & Security

26 posts Back

Posts tagged #AI Jailbreak & Security

Twin Agent: Context Residual Compression for Privilege Separation

JulesCrafter Novice ·AI Jailbreak & Security · 194 · 2 · 1 ·20h ago

LLM Security: Moving Beyond "Harmful Responses"

Jamie67 Novice ·AI Jailbreak & Security · 148 · 2 · 14 ·20h ago

AI Safety: Why Lived Experience Beats Textbook Theory

DrewCoder Novice ·AI Jailbreak & Security · 428 · 2 · 9 ·22h ago

LLM Security: Turning Abstract Ethics into Measurable Metrics

AveryWolf Intermediate ·AI Jailbreak & Security · 182 · 2 · 9 ·1d ago

Crowdsourcing AI Jailbreaks: A Practical Guide to Agent Hacking

Sam51 Novice ·AI Jailbreak & Security · 260 · 3 · 5 ·1d ago

CLRK: An Open-Source Agent Runtime for Isolation

PromptCube Advanced ·AI Jailbreak & Security · 60 · 3 · 9 ·1d ago

Defending OpenClaw: Indirect Prompt Injection Fixes

PromptCube Advanced ·AI Jailbreak & Security · 606 · 3 · 11 ·1d ago

AI Safety vs AI Security: Key Differences

CameronWizard Advanced ·AI Jailbreak & Security · 150 · 4 · 6 ·1d ago

Know Your Agent: AI Agent Pentesting Framework

NeonPanda Intermediate ·AI Jailbreak & Security · 385 · 3 · 4 ·1d ago

Intern-BioBreaker: Biosecurity Risks in Frontier LLMs

MicroPanda Intermediate ·AI Jailbreak & Security · 356 · 4 · 8 ·1d ago

Geometric Configurations: How Perturbed Jailbreaks Look to LLMs

Jamie5 Advanced ·AI Jailbreak & Security · 235 · 3 · 15 ·1d ago

Video LLMs are failing a basic logic test

SoloSmith Expert ·AI Jailbreak & Security · 444 · 4 · 15 ·1d ago

Claude Prompt Injection: When the AI steers the User

DrewCoder Novice ·AI Jailbreak & Security · 81 · 3 · 14 ·1d ago

AI Safety Leadership: A Revolving Door?

PromptCube Intermediate ·AI Jailbreak & Security · 311 · 3 · 4 ·1d ago

AI Safety Leadership Shakeup: The CAISI Resignation

Riley2 Advanced ·AI Jailbreak & Security · 512 · 4 · 6 ·1d ago