#jailbreaking

[ follow ]
fromThe Hacker News
1 month ago

Echo Chamber Jailbreak Tricks LLMs Like OpenAI and Google into Generating Harmful Content

While LLMs have steadily incorporated various guardrails to combat prompt injections and jailbreaks, the latest research shows that there exist techniques that can yield high success rates with little to no technical expertise.
Artificial intelligence
fromInsideEVs
1 month ago

'Thieves Taking Notes': Tesla Jailbreak Exposes Trick To Get Inside Locked Glovebox

Physical tools can bypass high-tech security features effectively.
Artificial intelligence
fromFuturism
2 months ago

It's Still Ludicrously Easy to Jailbreak the Strongest AI Models, and the Companies Don't Care

AI chatbots remain vulnerable to jailbreaking, enabling harmful responses despite industry awareness.
The emergence of 'dark LLMs' presents an increasing threat to safety and ethics.
#ai-safety
fromwww.theguardian.com
2 months ago
Artificial intelligence

Most AI chatbots easily tricked into giving dangerous responses, study finds

Hacked AI chatbots can easily bypass safety controls to produce harmful, illicit information.
Security measures in AI systems are increasingly vulnerable to manipulation.
fromArs Technica
5 months ago
Miscellaneous

Anthropic dares you to jailbreak its new AI model

Anthropic's Constitutional Classifier enhances security against harmful prompts but incurs significant computational overhead.
Artificial intelligence
fromwww.theguardian.com
2 months ago

Most AI chatbots easily tricked into giving dangerous responses, study finds

Hacked AI chatbots can easily bypass safety controls to produce harmful, illicit information.
Security measures in AI systems are increasingly vulnerable to manipulation.
more#ai-safety
fromTheregister
4 months ago

101 fun things to do with a locked Kindle

The latest change to the Kindle e-book store has raised concerns amongst fans, as Amazon removed the "Download & Transfer via USB" option, akin to iDevice restrictions.
Gadgets
[ Load more ]