19 stories tagged with #jailbreak, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Jailbreak"
Jailbreaking the Lululemon Mirror [video]
Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.…
Army 'Jailbreaks' Its Own Weapon Systems to Counter Drone Threats
Officials say software restrictions on weapons and radar systems slowed down efforts to detect incoming drones and missiles…
Multi-turn jailbreak rates across 15 frontier models (Grok 88%, Claude 12%)
The dominant safety benchmarks for frontier large language models share a structural assumption: that a single prompt and a single model response are enough to characterize how a m…
Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their e…
Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown…
Can you jailbreak Llama 3.1 8B? (Red-Teaming Challenge)
LLM Guard scored 0/8 on a USENIX 2025 multi-turn jailbreak. Here’s what caught it instead.
REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak
While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-…
Open-source LLMs are still weak against long reasoning jailbreaks, even with lightweight defenses
Open-source CLI for repeatable prompt-injection and jailbreak testing
Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models
Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning content. However, exposing a mo…
Amazon’s Kindle shutdown is sending users down the jailbreak rabbit hole
Amazon is retiring support for these Kindle models, and many users are finding unexpected ways to keep them alive.…
OG Kindle owners are staging a jailbreak revolt after Amazon cut support for their devices
The community is rekindling what Amazon wants to extinguish.…
The Psychopathy Jailbreak: What a Broken AI Teaches Us About Human Manipulation
How a Predator's Playbook Broke an AI - And How to Recognize It Before It Works on You…
Old kindle owners are revolting against Amazon’s support shutdown with jailbreaking
Amazon’s support cutoff has pushed parts of the Kindle community into open revolt, with jailbreaks becoming a way to fight planned obsolescence and keep working e-readers out of th…
Users turn to jailbreaking their older Kindles as Amazon ends support
Users turn to jailbreaking their older Kindles as Amazon ends support
It may be possible to jailbreak an older, end-of-support Kindle and continue adding books to it. But doing so carries risks.…
What Is AI Jailbreaking? A Beginner's Guide to the Cat-and-Mouse Game Behind Every Chatbot
Jailbreaking went from cracking iPhones to liberating LLMs. Here's how it works, who's doing it, and why every AI lab is losing sleep.…
Meet the AI jailbreakers: ‘I see the worst things humanity has produced’
To test the safety and security of AI, hackers have to trick large language models into breaking their own rules. It requires ingenuity and manipulation - and can come at a deep em…