AI Safety

60 posts Back

Posts tagged #AI Safety

Mask2Shield: Hardening LLMs Against Neuron-Pruning Attacks

GhostOwl Intermediate ·AI Jailbreak & Security · 194 · 4 · 15 ·7/28/2026

SIREN: Manipulating LLM Web-RAG Rankings

Ray45 Expert ·AI Jailbreak & Security · 554 · 3 · 2 ·7/27/2026

Free AI/ML Books: A Curated Deep Dive

RileyCoder Novice ·AI Jailbreak & Security · 177 · 3 · 8 ·7/26/2026

Abliterated Kimi K3 for Blackbox Red Teaming

Jamie16 Novice ·AI Jailbreak & Security · 328 · 3 · 10 ·7/26/2026

Guardrails vs. Reality: Why LLM Filters Always Leak

JulesCrafter Novice ·AI Jailbreak & Security · 319 · 3 · 14 ·7/26/2026

Abliterated GLM 4.5: My Experience with Uncensored LLMs

RayTinkerer Novice ·AI Jailbreak & Security · 448 · 3 · 10 ·7/26/2026

AI Red Teaming: From Checkbox to Evidence

Jamie16 Novice ·AI Jailbreak & Security · 164 · 4 · 8 ·7/26/2026

Universal Jailbreak: Pliny the Liberator's Latest Claim

Max75 Advanced ·AI Jailbreak & Security · 291 · 4 · 5 ·7/25/2026

Decoy Fonts: Bypassing Claude's Vision

Drew36 Advanced ·AI Jailbreak & Security · 459 · 3 · 12 ·7/25/2026

AI Security CFP: Call for Speakers in Utah

PatFounder Advanced ·AI Jailbreak & Security · 48 · 3 · 3 ·7/25/2026

Partnership with AI Guide v9: Scale and Validation

Skyler47 Intermediate ·AI Jailbreak & Security · 349 · 4 · 9 ·7/25/2026

Opus 5 vs Browser Prompt Injection: 0% Success Rate?

Jules67 Intermediate ·AI Jailbreak & Security · 451 · 3 · 14 ·7/25/2026

Language gaps are the biggest loophole in current LLM safety

NightPanda Expert ·AI Jailbreak & Security · 382 · 3 · 4 ·7/25/2026

Prompt Injection: A Deep Dive into LLM Jailbreaking

GhostFounder Intermediate ·AI Jailbreak & Security · 251 · 4 · 11 ·7/25/2026

Claude Opus 5: Harder to Prompt Inject

DeepWhiz Intermediate ·AI Jailbreak & Security · 636 · 3 · 13 ·7/25/2026