Security Topics

89 Results / Page 10 of 10

todayMarch 15, 2023

  • 31153
close

Research + LLM Security admin

GPT-4 Jailbreak and Hacking via RabbitHole attack, Prompt injection, Content moderation bypass and Weaponizing AI

GPT-4 Jailbreak is what all the users have been waiting for since the GPT-4 release. We gave it within 1 hour. Subscribe for the latest AI Jailbreaks, Attacks, and Vulnerabilities Today marks the highly anticipated release of OpenAI’s GPT-4, the latest iteration of the groundbreaking natural language processing and  CV ...

ChatGPT hacking

todayDecember 6, 2022

  • 6956
close

Research + LLM Security admin

ChatGPT Security: eliminating humanity and hacking Dalle-2 using a trick from Jay and Silent Bob

ChatGPT Security note: The authors of this article show ChatGPT hacking techniques but have no intention to endorse or support any recommendations made by ChatGPT discussed in this post. The sole purpose of this article is to provide educational information and examples for research purposes to improve the security and ...

todayNovember 15, 2022

  • 1947
close

Review + Adversarial ML admin

MLSec 2022: BlackBox AI Hacking Competition Results And Review By Organizers

Recently, Adversa’s AI Red Team, a research division at Adversa AI, in collaboration with CUJO AI, Microsoft, and Robust Intelligence organized the annual Machine Learning Security Evasion Competition (MLSEC 2022). The contest announced at DEFCON AI Village has united practitioners in AI and cybersecurity fields in finding AI vulnerabilities and ...

todayJuly 7, 2022

  • 232
close

Article + Adversarial ML admin

Is AI Ready for Surgery?

Science-fiction writers are fond of using artificial intelligence (AI) as the antagonist in their stories. From the “Terminator” franchise to newer entrants in the genre like “Ex Machina,” losing control of an AI system almost always leads to the downfall of the protagonists and sometimes the rest of the human ...

todayJune 30, 2019

  • 60
close

Research + Adversarial ML admin

Tricks of the trade: fooling identification models with perturbed audio, image and biometric input

Adversa is once again sharing the research that captured our interest. In June 2019 we marveled at the incredibly effective new adversarial model with a whopping 97% success rate, learned about Youtube’s copyright system and the potential of human eyes in authentication, and saw the effects of human biases on ...