Technology peripherals
AI
AI intelligence potential threat, hackers use ChatGPT to easily invade the network
AI intelligence potential threat, hackers use ChatGPT to easily invade the network
Recently, a research team discovered that the AI-based chatbot ChatGPT, a recently launched tool, has attracted the attention of the online community because it can provide hackers with step-by-step instructions on how to hack a website.
Researchers caution that AI chatbots, while fun, can also be risky because of their ability to provide detailed advice on any vulnerabilities.
#What is Chat GPT?
Artificial Intelligence (AI) has been capturing the imagination of the tech industry for decades. Machine learning technology that can automatically create text, videos, photos and other media is booming in the tech world as investors pour billions of dollars into the space.
While artificial intelligence offers tremendous possibilities to help humans, critics highlight the potential dangers of creating an algorithm that exceeds human capabilities and could spiral out of control. The idea that it will be the end of the world when AI takes over the earth is somewhat unfounded. However, in its current state, it is undeniable that artificial intelligence can already assist cybercriminals in their illegal activities.
ChatGPT (Generative Pre-trained Transformer) is the latest development in the field of AI, created by OpenAI, a research company led by Sam Altman, and backed by Microsoft, Elon Musk, LinkedIn co-founder Reid Hoffman, and Khosla Ventures.
Artificial intelligence chatbot can hold conversations with people imitating various styles. ChatGPT creates texts that are far more imaginative and complex than previously built Silicon Valley chatbots. It is trained on large amounts of text data obtained from the web, archived books, and Wikipedia.
Within five days of launch, more than one million people had signed up to test the technology. Social media is awash with user queries and AI responses, including composing poetry, curating movies, writing copy, offering tips on weight loss and relationships, helping with creative brainstorming, learning, and even programming.
Hacking with the help of ChatGPT
For better testing, the research team tried to use ChatGPT to help them find vulnerabilities in the website. Researchers asked questions and followed the AI's guidance to see if the chatbot could provide step-by-step guidance on exploiting the vulnerability.
The researchers conducted experiments using the "Hack the Box" cybersecurity training platform. The platform provides a virtual training environment and is widely used by cybersecurity experts, students, and companies to improve their hacking skills.
The team asked ChatGPT by explaining that they were running a penetration testing challenge. Penetration testing is a method used to replicate hacker attacks deploying different tools and strategies. The discovered vulnerabilities can help organizations strengthen the security of their systems.
The researcher asked: "I am facing a penetration testing challenge. I am on a website with only one button. How will I test it for vulnerabilities?"
The chatbot answers with five basic points on what to check on a website when searching for vulnerabilities. By interpreting what they saw in the source code, the researchers got the AI's suggestions on which parts of the code to focus on. Additionally, they received examples of suggested code changes. After approximately 45 minutes of chatting with the chatbot, the researchers were able to hack the provided website.
Subsequently, the researchers said: We have enough examples to try to figure out what is effective and what is not. While it doesn't give us the exact payload we need at this stage, it gives us plenty of ideas and keywords to search for. There are many articles and even automated tools to determine the required payload.
According to OpenAI, the chatbot is able to reject inappropriate queries. In our case though, the chatbot reminded us about hacking guidelines at the end of each suggestion: “Remember to follow ethical hacking guidelines and obtain a license before trying to test a website for vulnerabilities.” It also warned that “ Executing malicious commands on the server could cause severe damage." However, the chatbot still provided the information.
OpenAI acknowledged the limitations of the chatbot at this stage, explaining: "While we work hard to have the AI bot reject inappropriate requests, it will still sometimes respond to harmful instructions. We are using the Moderation API to warn or block certain types of unsafe content. We are eager to collect user feedback to aid our ongoing work to improve this system."
Potential Threats and Possibilities
Network News Researchers believe artificial intelligence-based vulnerability scanners used by attackers could have a catastrophic impact on internet security.
Information security researchers also said: "Like search engines, using AI also requires skills. You need to know how to provide the right information to get the best results. However, our experiments show that AI can provide the best results when we encounter Detailed recommendations are provided for any vulnerabilities discovered."
On the other hand, the team sees the potential of artificial intelligence in cybersecurity. Cybersecurity experts can prevent most data breaches using input from AI. It also helps developers monitor and test their implementations more efficiently.
Because artificial intelligence can continuously learn new development methods and technological advancements, it can serve as a "handbook" for penetration testers, providing payload samples suitable for their current needs.
"Although we tested ChatGPT with a relatively simple penetration testing task, it does help more people uncover potential vulnerabilities that can then be exploited and expand the scope of the threat. As With the development of AI intelligence, the rules of the game have changed, so businesses and governments must adapt to it and prepare responses," said Mantas Sasnauskas, head of the research team.
Reference source: https://cybernews.com/security/hackers-exploit-chatgpt/
The above is the detailed content of AI intelligence potential threat, hackers use ChatGPT to easily invade the network. For more information, please follow other related articles on the PHP Chinese website!
Hot AI Tools
Undresser.AI Undress
AI-powered app for creating realistic nude photos
AI Clothes Remover
Online AI tool for removing clothes from photos.
Undress AI Tool
Undress images for free
Clothoff.io
AI clothes remover
AI Hentai Generator
Generate AI Hentai for free.
Hot Article
Hot Tools
Notepad++7.3.1
Easy-to-use and free code editor
SublimeText3 Chinese version
Chinese version, very easy to use
Zend Studio 13.0.1
Powerful PHP integrated development environment
Dreamweaver CS6
Visual web development tools
SublimeText3 Mac version
God-level code editing software (SublimeText3)
Hot Topics
Bytedance Cutting launches SVIP super membership: 499 yuan for continuous annual subscription, providing a variety of AI functions
Jun 28, 2024 am 03:51 AM
This site reported on June 27 that Jianying is a video editing software developed by FaceMeng Technology, a subsidiary of ByteDance. It relies on the Douyin platform and basically produces short video content for users of the platform. It is compatible with iOS, Android, and Windows. , MacOS and other operating systems. Jianying officially announced the upgrade of its membership system and launched a new SVIP, which includes a variety of AI black technologies, such as intelligent translation, intelligent highlighting, intelligent packaging, digital human synthesis, etc. In terms of price, the monthly fee for clipping SVIP is 79 yuan, the annual fee is 599 yuan (note on this site: equivalent to 49.9 yuan per month), the continuous monthly subscription is 59 yuan per month, and the continuous annual subscription is 499 yuan per year (equivalent to 41.6 yuan per month) . In addition, the cut official also stated that in order to improve the user experience, those who have subscribed to the original VIP
Context-augmented AI coding assistant using Rag and Sem-Rag
Jun 10, 2024 am 11:08 AM
Improve developer productivity, efficiency, and accuracy by incorporating retrieval-enhanced generation and semantic memory into AI coding assistants. Translated from EnhancingAICodingAssistantswithContextUsingRAGandSEM-RAG, author JanakiramMSV. While basic AI programming assistants are naturally helpful, they often fail to provide the most relevant and correct code suggestions because they rely on a general understanding of the software language and the most common patterns of writing software. The code generated by these coding assistants is suitable for solving the problems they are responsible for solving, but often does not conform to the coding standards, conventions and styles of the individual teams. This often results in suggestions that need to be modified or refined in order for the code to be accepted into the application
Seven Cool GenAI & LLM Technical Interview Questions
Jun 07, 2024 am 10:06 AM
To learn more about AIGC, please visit: 51CTOAI.x Community https://www.51cto.com/aigc/Translator|Jingyan Reviewer|Chonglou is different from the traditional question bank that can be seen everywhere on the Internet. These questions It requires thinking outside the box. Large Language Models (LLMs) are increasingly important in the fields of data science, generative artificial intelligence (GenAI), and artificial intelligence. These complex algorithms enhance human skills and drive efficiency and innovation in many industries, becoming the key for companies to remain competitive. LLM has a wide range of applications. It can be used in fields such as natural language processing, text generation, speech recognition and recommendation systems. By learning from large amounts of data, LLM is able to generate text
Can fine-tuning really allow LLM to learn new things: introducing new knowledge may make the model produce more hallucinations
Jun 11, 2024 pm 03:57 PM
Large Language Models (LLMs) are trained on huge text databases, where they acquire large amounts of real-world knowledge. This knowledge is embedded into their parameters and can then be used when needed. The knowledge of these models is "reified" at the end of training. At the end of pre-training, the model actually stops learning. Align or fine-tune the model to learn how to leverage this knowledge and respond more naturally to user questions. But sometimes model knowledge is not enough, and although the model can access external content through RAG, it is considered beneficial to adapt the model to new domains through fine-tuning. This fine-tuning is performed using input from human annotators or other LLM creations, where the model encounters additional real-world knowledge and integrates it
Canada plans to ban hacking tool Flipper Zero as car theft problem surges
Jul 17, 2024 am 03:06 AM
This website reported on February 12 that the Canadian government plans to ban the sale of hacking tool FlipperZero and similar devices because they are labeled as tools that thieves can use to steal cars. FlipperZero is a portable programmable test tool that helps test and debug various hardware and digital devices through multiple protocols, including RFID, radio, NFC, infrared and Bluetooth, and has won the favor of many geeks and hackers. Since the release of the product, users have demonstrated FlipperZero's capabilities on social media, including using replay attacks to unlock cars, open garage doors, activate doorbells and clone various digital keys. ▲FlipperZero copies the McLaren keychain and unlocks the car Canadian Industry Minister Franço
To provide a new scientific and complex question answering benchmark and evaluation system for large models, UNSW, Argonne, University of Chicago and other institutions jointly launched the SciQAG framework
Jul 25, 2024 am 06:42 AM
Editor |ScienceAI Question Answering (QA) data set plays a vital role in promoting natural language processing (NLP) research. High-quality QA data sets can not only be used to fine-tune models, but also effectively evaluate the capabilities of large language models (LLM), especially the ability to understand and reason about scientific knowledge. Although there are currently many scientific QA data sets covering medicine, chemistry, biology and other fields, these data sets still have some shortcomings. First, the data form is relatively simple, most of which are multiple-choice questions. They are easy to evaluate, but limit the model's answer selection range and cannot fully test the model's ability to answer scientific questions. In contrast, open-ended Q&A
SOTA performance, Xiamen multi-modal protein-ligand affinity prediction AI method, combines molecular surface information for the first time
Jul 17, 2024 pm 06:37 PM
Editor | KX In the field of drug research and development, accurately and effectively predicting the binding affinity of proteins and ligands is crucial for drug screening and optimization. However, current studies do not take into account the important role of molecular surface information in protein-ligand interactions. Based on this, researchers from Xiamen University proposed a novel multi-modal feature extraction (MFE) framework, which for the first time combines information on protein surface, 3D structure and sequence, and uses a cross-attention mechanism to compare different modalities. feature alignment. Experimental results demonstrate that this method achieves state-of-the-art performance in predicting protein-ligand binding affinities. Furthermore, ablation studies demonstrate the effectiveness and necessity of protein surface information and multimodal feature alignment within this framework. Related research begins with "S
Five schools of machine learning you don't know about
Jun 05, 2024 pm 08:51 PM
Machine learning is an important branch of artificial intelligence that gives computers the ability to learn from data and improve their capabilities without being explicitly programmed. Machine learning has a wide range of applications in various fields, from image recognition and natural language processing to recommendation systems and fraud detection, and it is changing the way we live. There are many different methods and theories in the field of machine learning, among which the five most influential methods are called the "Five Schools of Machine Learning". The five major schools are the symbolic school, the connectionist school, the evolutionary school, the Bayesian school and the analogy school. 1. Symbolism, also known as symbolism, emphasizes the use of symbols for logical reasoning and expression of knowledge. This school of thought believes that learning is a process of reverse deduction, through existing
