Lukas Aichberger
@aichberger.bsky.social
Machine Learning ELLIS PhD at Johannes Kepler University Linz and University of Oxford
Reposted by Lukas Aichberger
Hot take: I think we just demonstrated the first AI agent computer worm 🤔
When an agent sees a trigger image it's instructed to execute malicious code and then share the image on social media to trigger other users' agents
This is a chance to talk about agent security 👇
When an agent sees a trigger image it's instructed to execute malicious code and then share the image on social media to trigger other users' agents
This is a chance to talk about agent security 👇
⚠️ Beware: Your AI assistant could be hijacked just by encountering a malicious image online!
Our latest research exposes critical security risks in AI assistants. An attacker can hijack them by simply posting an image on social media and waiting for it to be captured. [1/6] 🧵
Our latest research exposes critical security risks in AI assistants. An attacker can hijack them by simply posting an image on social media and waiting for it to be captured. [1/6] 🧵
March 20, 2025 at 2:28 PM
Hot take: I think we just demonstrated the first AI agent computer worm 🤔
When an agent sees a trigger image it's instructed to execute malicious code and then share the image on social media to trigger other users' agents
This is a chance to talk about agent security 👇
When an agent sees a trigger image it's instructed to execute malicious code and then share the image on social media to trigger other users' agents
This is a chance to talk about agent security 👇
⚠️ Beware: Your AI assistant could be hijacked just by encountering a malicious image online!
Our latest research exposes critical security risks in AI assistants. An attacker can hijack them by simply posting an image on social media and waiting for it to be captured. [1/6] 🧵
Our latest research exposes critical security risks in AI assistants. An attacker can hijack them by simply posting an image on social media and waiting for it to be captured. [1/6] 🧵
March 18, 2025 at 6:25 PM
⚠️ Beware: Your AI assistant could be hijacked just by encountering a malicious image online!
Our latest research exposes critical security risks in AI assistants. An attacker can hijack them by simply posting an image on social media and waiting for it to be captured. [1/6] 🧵
Our latest research exposes critical security risks in AI assistants. An attacker can hijack them by simply posting an image on social media and waiting for it to be captured. [1/6] 🧵
Reposted by Lukas Aichberger
Often LLMs hallucinate because of semantic uncertainty due to missing factual training data. We propose a method to detect such uncertainties using only one generated output sequence. Super efficient method to detect hallucination in LLMs.
𝗡𝗲𝘄 𝗣𝗮𝗽𝗲𝗿 𝗔𝗹𝗲𝗿𝘁: Rethinking Uncertainty Estimation in Natural Language Generation 🌟
Introducing 𝗚-𝗡𝗟𝗟, a theoretically grounded and highly efficient uncertainty estimate, perfect for scalable LLM applications 🚀
Dive into the paper: arxiv.org/abs/2412.15176 👇
Introducing 𝗚-𝗡𝗟𝗟, a theoretically grounded and highly efficient uncertainty estimate, perfect for scalable LLM applications 🚀
Dive into the paper: arxiv.org/abs/2412.15176 👇
Rethinking Uncertainty Estimation in Natural Language Generation
Large Language Models (LLMs) are increasingly employed in real-world applications, driving the need to evaluate the trustworthiness of their generated text. To this end, reliable uncertainty estimatio...
arxiv.org
December 20, 2024 at 12:52 PM
Often LLMs hallucinate because of semantic uncertainty due to missing factual training data. We propose a method to detect such uncertainties using only one generated output sequence. Super efficient method to detect hallucination in LLMs.
𝗡𝗲𝘄 𝗣𝗮𝗽𝗲𝗿 𝗔𝗹𝗲𝗿𝘁: Rethinking Uncertainty Estimation in Natural Language Generation 🌟
Introducing 𝗚-𝗡𝗟𝗟, a theoretically grounded and highly efficient uncertainty estimate, perfect for scalable LLM applications 🚀
Dive into the paper: arxiv.org/abs/2412.15176 👇
Introducing 𝗚-𝗡𝗟𝗟, a theoretically grounded and highly efficient uncertainty estimate, perfect for scalable LLM applications 🚀
Dive into the paper: arxiv.org/abs/2412.15176 👇
Rethinking Uncertainty Estimation in Natural Language Generation
Large Language Models (LLMs) are increasingly employed in real-world applications, driving the need to evaluate the trustworthiness of their generated text. To this end, reliable uncertainty estimatio...
arxiv.org
December 20, 2024 at 11:44 AM
𝗡𝗲𝘄 𝗣𝗮𝗽𝗲𝗿 𝗔𝗹𝗲𝗿𝘁: Rethinking Uncertainty Estimation in Natural Language Generation 🌟
Introducing 𝗚-𝗡𝗟𝗟, a theoretically grounded and highly efficient uncertainty estimate, perfect for scalable LLM applications 🚀
Dive into the paper: arxiv.org/abs/2412.15176 👇
Introducing 𝗚-𝗡𝗟𝗟, a theoretically grounded and highly efficient uncertainty estimate, perfect for scalable LLM applications 🚀
Dive into the paper: arxiv.org/abs/2412.15176 👇