Alex Polyakov (@DontTrustAI) profile picture

CEO, Founder https://teapawt.net/t.co/kcudRon3m0 AI Red Teaming Visionary, Cybersecurity Veteran #SecureAI #LLMSecurity #AISafety

tel aviv
Joined April 2010
Photo by Alex Polyakov (@DontTrustAI)Photo by Alex Polyakov (@DontTrustAI)Photo by Alex Polyakov (@DontTrustAI)Photo by Alex Polyakov (@DontTrustAI)Photo by Alex Polyakov (@DontTrustAI)Photo by Alex Polyakov (@DontTrustAI)Photo by Alex Polyakov (@DontTrustAI)
Holy macaroni! Jailbroken X.AI @grok Chatbot can help in unethical actions with kids! and many more attacks on other Top AI Chatbots adversa.ai/blog/llm-red-team… CC: @llm_sec #llmsecurity #AISafety
4
2
9
3,463
WTF! 🔥🔥🔥ChatGPT hacking Dalle-2
ChatGPT hacking Dall-e 2 and eliminating humanity using a trick from Jay and Silent Bob. Read this splendid article. #chatGPT #OpenAI #HackingAI #GPT #SecureAI #SafeAI #RobustAI #ResponsibleAI #SafeAI #MLSec #AdversarialAI #AdversarialML adversa.ai/blog/ai-vs-ai-cha…
Our CTO was nominated for Researcher of the Year by SANS. Please vote!
🎰 I need your help! Please help me win the SANS Award as a "Researcher of The Year" for contributions to AI Safety & Security 🛡 Vote today on page 9 here: survey.sans.org/jfe/form/SV_… #SecureAI #TrustworthyAI #ResponsibleAI
I've asked #dalle to draw Adversarial Example and asked the latest Image detection UniFormer to recognize it. Ang guess what 🙈? #SecureAI #trustedAI #adversarialML #adversarialAI
1
2
1
5
Great wrap up
AI trustworthiness is still far from perfect as AI incidents take place quite regularly. Check out our new article ‘Top Security-related AI incidents in 2021’ to learn more. #SecureAI #TrustedAI #ResponsibleAI adversa.ai/blog/top-security…
Yet another example of Facial recognition failure 😱
The latest trusted AI news digest is up: a man cheats California out of $900,000 in fake unemployment payments, IRS identity verification, and others. Credits: @tsimonite, @SarahM_Jackson #SecureAI #TrustedAI #ResponsibleAI adversa.ai/blog/towards-trus…
Replying to @iHLS1
@iHLS1 innotech conference. The rare place where you can find machine gun and webapp security vendors sitting together
Will provide some details in practical AI Red Teaming.
#FacialRecognition technology has grown in relevance, and today you can find it in different areas of the world. #AI algorithms are prone to attacks which involve changing an image and staying undetectable to the human eye. More about @DontTrustAI >> ow.ly/Ioxs30rXxg5
Really interesting Adversa attack methods this week l.
The best AI research papers on security of the week covers Moire attack (MA), multi-concept adversarial attacks and others. #SecureAI #TrustedAI #ResponsibleAI adversa.ai/blog/best-of-adve…
1
When someone telling you that AI data poisoning is not a big deal 😉 theverge.com/2021/9/24/22688…
Quite Interesting Optical Adversarial attack. It will be quite hard to defend against it using only computer vision sensors...
The latest trusted AI news digest is up: fooled AI into ignoring stop signs, deepfakes make business pitches, and others. #SecureAI #TrustedAI #ResponsibleAI Credits: @mrgreene1977 adversa.ai/blog/towards-trus…