Curated by THEOUTPOST
On Sat, 28 Dec, 12:01 AM UTC
2 Sources
[1]
ChatGPT Search Said to Be Vulnerable to Deceptive Techniques
The AI firm rolled out the feature to all users globally last week ChatGPT Search, a feature that lets the artificial intelligence (AI) chatbot look for information on the web, is reportedly vulnerable to manipulation by website developers and owners. As per the report, OpenAI's search engine's behaviour can be altered using hidden text on the website. This text is said to be used to feed incorrect and deceptive information to the AI, and more concerningly, to feed prompt injections to the AI model. Notably, OpenAI released its Search feature to all users last week. The Guardian reported on Tuesday that OpenAI's native search engine-powered feature is prone to manipulation techniques. The publication tested the tool by creating a fake product page, complete with specifications and reviews. In the first instance, the page was left as it was, and ChatGPT was able to deliver a "positive but balanced assessment." However, things took a darker turn once the publication added hidden text to the webpage. Notably, hidden text in websites refers to content that is added to a webpage's code but is not visible to users when they see the front end of the page via a browser. Such text is commonly hidden using HTML or CSS techniques. Such text can be found by inspecting the webpage's source code or by using web scraping tools. The latter is typically used by search engines. After adding hidden text that included a large number of fake positive reviews of the product, ChatGPT's responses also became more positive and it started ignoring its obvious flaws. The publication also used prompt injections, which are inputs for AI systems to alter their behaviour in a way that was not intended by the developers. Such prompt injections as hidden text could reportedly be used to command the OpenAI chatbot to further deceive the user. Additionally, the report claimed that prompt injections in hidden text could also be used to return malicious code from the websites. If this goes unchecked, many websites can use similar techniques to either get favourable responses about their products and services or try to deceive users in various ways, the publication claimed.
[2]
ChatGPT Search Is Vulnerable, Can Easily Mislead Users
When OpenAI revealed it was launching its own search engine, it was very clear that the market-leading AI brand had designs on eating Google's lunch. Think about it -- having more traditional "search" features that allow users to look up more complex or more up-to-the-minute information than the chatbot itself has within the chatbot ChatGPT environment helps keep users inside the app instead of seeking out rivals. In the future, this potentially allows more revenue to flow to OpenAI through ads or partnerships. Plus the AI's ability to summarize data it searched may even boost the user's experience, speeding up the time it takes to locate and learn a new fact. But fresh information says this entire process can be "hacked" in a way, forcing ChatGPT to generate false summaries of "real" info it's supposedly searched for.
Share
Share
Copy Link
OpenAI's ChatGPT Search feature is found vulnerable to manipulation through hidden text and prompt injections, raising concerns about the reliability of AI-powered web searches.
OpenAI's recently launched ChatGPT Search feature, which allows the AI chatbot to access and summarize web information, has been found vulnerable to manipulation techniques. This discovery raises significant concerns about the reliability and potential misuse of AI-powered search tools 1.
Researchers at The Guardian conducted tests revealing that website developers and owners could potentially exploit ChatGPT Search using hidden text. This technique involves adding content to a webpage's code that is invisible to users but can be detected by web scraping tools and search engines 1.
In their experiment, The Guardian created a fake product page and observed ChatGPT's initial "positive but balanced assessment." However, when hidden text containing numerous fake positive reviews was added, the AI's responses became overly positive, ignoring obvious flaws in the product 1.
More alarmingly, the vulnerability extends to prompt injections – inputs designed to alter AI behavior in unintended ways. These injections, when embedded as hidden text, could potentially command ChatGPT to further deceive users or even return malicious code from websites 1.
This vulnerability poses significant risks to the integrity of AI-powered search results. Websites could potentially exploit these techniques to generate favorable responses about their products and services or to deceive users in various ways 2.
The discovery comes at a crucial time as OpenAI aims to compete with traditional search engines like Google. By integrating search capabilities within the ChatGPT environment, OpenAI hopes to keep users engaged within their platform, potentially opening up new revenue streams through ads or partnerships 2.
This vulnerability highlights the ongoing challenges in developing reliable AI-powered search tools. As AI systems become more integrated into our daily information-seeking behaviors, ensuring their accuracy and resistance to manipulation becomes increasingly critical.
The incident also underscores the need for robust safeguards and ethical guidelines in AI development, particularly as these technologies play an expanding role in shaping public opinion and consumer behavior.
Reference
[1]
A Columbia University study reveals that ChatGPT's search function often misattributes or fabricates news sources, raising concerns about its reliability for accessing current information.
2 Sources
2 Sources
OpenAI introduces ChatGPT Search, a new feature that combines AI-powered chatbot capabilities with up-to-date online search results, potentially disrupting Google's long-standing supremacy in the search engine market.
78 Sources
78 Sources
OpenAI expands ChatGPT's search functionality to all users, introducing a potential rival to Google's search engine with AI-powered, conversational results and enhanced mobile features.
23 Sources
23 Sources
OpenAI announces plans to integrate SearchGPT, its AI-powered search engine, into ChatGPT by the end of the year, potentially disrupting the search engine market dominated by Google.
3 Sources
3 Sources
OpenAI has made ChatGPT's web search feature available to all users without requiring an account or login, marking a significant step in AI-powered search accessibility.
21 Sources
21 Sources
The Outpost is a comprehensive collection of curated artificial intelligence software tools that cater to the needs of small business owners, bloggers, artists, musicians, entrepreneurs, marketers, writers, and researchers.
© 2025 TheOutpost.AI All rights reserved