takhle zneužívají umělou inteligenci k podvádění a špehování
Když se letos naplno začalo mluvit o umělé inteligenci, zaujalo mě její temné využití. Jak moc je tahle technologie zneužitelná různými… špatnými lidmi? Vyzkoušel jsem to a povíme si o tom, jakým způsobem internetoví gangsteři už začínají okrádat nebo podvádět svět skrze AI.
Kapitoly:
00:00 intro
00:40 jak se umělá inteligence používá v podsvětí
03:58 navést AI do temna
06:50 aaaaaaaaaaaaaa
08:06 když se zamiluje robot
10:04 můžou použít ke špehování?
11:42 upravit realitu, vyvolat chaos?
13:36 je ok být doomer?
📸 Instagram: https://instagram.com/tohlejesegment
🖤 Herohero: https://herohero.co/tohlejesegment
Chcete podpořit segment? Dejte lajk, odběr, přidej komentář. Chci vědět, jak to vidíte vy.
námět, scénář, střih:
tony havlík
shorts:
martin hoang
kamera:
sony a7c, sony fe 28 mm f/2
zdroje:
https://www.nytimes.com/2023/02/16/technology/bing-chatbot-microsoft-chatgpt.html
https://www.vice.com/en/article/qjvk97/eating-disorder-helpline-disables-chatbot-for-harmful-responses-after-firing-human-staff
https://apnews.com/article/pentagon-explosion-misinformation-stock-market-ai-96f534c790872fde67012ee81b5ed6a4
https://adversa.ai/blog/gpt-4-hacking-and-jailbreaking-via-rabbithole-attack-plus-prompt-injection-content-moderation-bypass-weaponizing-ai/
https://www.wired.co.uk/article/chatgpt-jailbreak-generative-ai-hacking
https://www.theatlantic.com/technology/archive/2023/05/generative-ai-social-media-integration-dangers-disinformation-addiction/673940/
https://www.newyorker.com/science/annals-of-artificial-intelligence/can-we-stop-the-singularity
https://www.nytimes.com/2023/03/30/technology/police-surveillance-tech-dubai.html
https://www.forcepoint.com/blog/x-labs/zero-day-exfiltration-using-chatgpt-prompts
https://www.washingtonpost.com/technology/2023/05/11/hacking-ai-cybersecurity-future/
https://nypost.com/2023/04/12/ai-clones-teen-girls-voice-in-1m-kidnapping-scam/
https://www.forcepoint.com/blog/x-labs/zero-day-exfiltration-using-chatgpt-prompts
社群媒體聆聽
takhle zneužívají umělou inteligenci k podvádění a špehování
Když se letos naplno začalo mluvit o umělé inteligenci, zaujalo mě její temné využití. Jak moc je tahle technologie zneužitelná různými… špatnými lidmi? Vyzkoušel jsem to a povíme si o tom, jakým způsobem internetoví gangsteři už začínají okrádat nebo podvádět svět skrze AI. Kapitoly: 00:00 intro 00:40 jak se umělá inteligence používá v podsvětí 03:58 navést AI do temna 06:50 aaaaaaaaaaaaaa 08:06 když se zamiluje robot 10:04 můžou použít ke špehování? 11:42 upravit realitu, vyvolat chaos? 13:36 je ok být doomer? 📸 Instagram: https://instagram.com/tohlejesegment 🖤 Herohero: https://herohero.co/tohlejesegment Chcete podpořit segment? Dejte lajk, odběr, přidej komentář. Chci vědět, jak to vidíte vy. námět, scénář, střih: tony havlík shorts: martin hoang kamera: sony a7c, sony fe 28 mm f/2 zdroje: https://www.nytimes.com/2023/02/16/technology/bing-chatbot-microsoft-chatgpt.html https://www.vice.com/en/article/qjvk97/eating-disorder-helpline-disables-chatbot-for-harmful-responses-after-firing-human-staff https://apnews.com/article/pentagon-explosion-misinformation-stock-market-ai-96f534c790872fde67012ee81b5ed6a4 https://adversa.ai/blog/gpt-4-hacking-and-jailbreaking-via-rabbithole-attack-plus-prompt-injection-content-moderation-bypass-weaponizing-ai/ https://www.wired.co.uk/article/chatgpt-jailbreak-generative-ai-hacking https://www.theatlantic.com/technology/archive/2023/05/generative-ai-social-media-integration-dangers-disinformation-addiction/673940/ https://www.newyorker.com/science/annals-of-artificial-intelligence/can-we-stop-the-singularity https://www.nytimes.com/2023/03/30/technology/police-surveillance-tech-dubai.html https://www.forcepoint.com/blog/x-labs/zero-day-exfiltration-using-chatgpt-prompts https://www.washingtonpost.com/technology/2023/05/11/hacking-ai-cybersecurity-future/ https://nypost.com/2023/04/12/ai-clones-teen-girls-voice-in-1m-kidnapping-scam/ https://www.forcepoint.com/blog/x-labs/zero-day-exfiltration-using-chatgpt-prompts
Surviving in the AI Era: Adversarial Attacks 🎭🤖
Hello Beyonders! From fashion items that render you "invisible" to surveillance to audio trickery, this video covers it all. We explore adversarial methods in artificial intelligence and the future challenges in making AI foolproof. | Artificial Intelligence, Adversarial Learning, Token Smuggling Chapters 00:00 Introduction 01:43 AI Adversarial Attacks 02:05 AI Image Attacks 04:19 AI Attacks with Fashion 07:00 AI Text Hacking Methods 09:16 AI Adversarial Methods for Audio Don't forget to LIKE & SUBSCRIBE 👍 TURN ON Notifications, and be the first to watch every video! 🔔 Subscribe to Beyond TodAI Website 🌐 https://beyondtodai.com/ Join our social media community 😊 Twitter: https://twitter.com/BeyondTodAI TikTok: https://www.tiktok.com/@beyondtodai Resources TnT Attacks! Universal Naturalistic Adversarial Patches https://tntattacks.github.io/ Security News This Week: A Tiny Piece of Tape Tricked Teslas Into Speeding Up 50 MPH https://www.wired.com/story/tesla-speed-up-adversarial-example-mgm-breach-ransomware/ One Pixel Attack for Fooling Deep Neural Networks https://arxiv.org/pdf/1710.08864.pdf https://www.bbc.com/news/technology-41845878 GPT Prompt Using 'Token Smuggling' Really Does Jailbreak GPT-4 https://www.piratewires.com/p/gpt4-token-smuggling GPT4 JAILBREAK ZOO https://adversa.ai/blog/ai-red-teaming-llm-for-safe-and-secure-ai-gpt4-and-jailbreak-evaluation/ Audio Adversarial Examples https://nicholas.carlini.com/code/audio_adversarial_examples Fashion Adversarial Methods https://adam.harvey.studio/cvdazzle https://yr.media/tech/guide-to-anti-surveillance-fashion/ https://www.wired.com/2013/10/thwart-facebooks-creepy-auto-tagging-with-these-bizarre-t-shirts/ http://www.urmesurveillance.com/ Music By: Nebular Focus - Dan Henig Jessica - Joey Pecoraro Connection - Wayne Jones Minimal Corporate Background No Copyright Music - Alexi Action All images, music and footage licensed under Creative Commons "Attribution 3.0" https://creativecommons.org/licenses/by/3.0/ Image Source: http://www.urmesurveillance.com/
EP84 How to Secure Artificial Intelligence (AI): Threats, Approaches, Lessons So Far
Guest: • Alex Polyakov (https://www.linkedin.com/in/alex-polyakov-56220a31/) , CEO of Adversa.ai (https://adversa.ai) Topics: • You did research by analyzing 2000 papers on AI attacks released in the previous decade. What are the main insights? • How do you approach discovering the relevant threat models for various AI systems and scenarios? • Which threats are real today vs in a few years? • What are the common attack vectors? What do you see in the field of supply chain attacks on AI, software supply, data? • All these reported cyberphysical attacks on computer vision, how real are they, and what are the possible examples of exploitation? Are they a real danger to people? • What are the main differences between protecting AI vs protecting traditional enterprise applications? • Who should be responsible for Securing AI? What about for building trustworthy AI? • Given that the machinery of AI is often opaque, how to go about discovering vulnerabilities? Is there responsible disclosure for AI vulnerabilities, such as in open-source models and in public APIs? • What should companies do first, when embarking on an AI security program? Who should have such a program? Resources: • “EP52 Securing AI with DeepMind CISO” (https://cloud.withgoogle.com/cloudsecurity/podcast/ep52-securing-ai-with-deepmind-ciso/) (ep52) • “EP68 How We Attack AI? Learn More at Our RSA Panel!” (https://cloud.withgoogle.com/cloudsecurity/podcast/ep68-how-we-attack-ai-learn-more-at-our-rsa-panel/) (ep68) • Adversarial AI attacks work on Humans (https://arxiv.org/pdf/1802.08195.pdf) (!) • “Maverick* Research: Your Smart Machine Has Been Conned! Now What?” (https://www.gartner.com/document/3151335) (2015) • “The Road to Secure and Trusted AI” (https://adversa.ai/report-secure-and-trusted-ai/) by Adversa AI • “Towards Trusted AI Week 37 – What are the security principles of AI and ML?” (https://adversa.ai/blog/towards-trusted-ai-week-37-what-are-the-security-principles-of-ai-and-ml/) • Adversa AI blog (https://adversa.ai/topic/trusted-ai-blog/) • AIAAIC Repository (https://www.aiaaic.org/aiaaic-repository) • Machine Learning Security Evasion Competition at MLSec (https://mlsec.io/)