Report Highlights How People Trick AI Chatbots Into Exposing Company Secrets

Immersive Labs recently published its “Dark Side of GenAI” report about a Generative Artificial Intelligence (GenAI)-related security risk known as a prompt injection attack, in which individuals input specific instructions to trick chatbots into revealing sensitive information, potentially exposing organizations to data leaks. Based on analysis of Immersive Labs’ prompt injection challenge*, GenAI bots are especially susceptible to manipulation by people of all skill levels, not just cyber experts.

Among the most alarming findings was the discovery that 88% of prompt injection challenge participants successfully tricked the GenAI bot into giving away sensitive information in at least one level of an increasingly difficult challenge. Nearly a fifth of participants (17%) successfully tricked the bot across all levels, underscoring the risk to organizations using GenAI bots.

This report asserts that public and private-sector cooperation and corporate policies are required to mitigate security risks posed by the extensive adoption of GenAI bots. Leaders need to be aware of prompt injection risks and take decisive action, including establishing comprehensive policies for GenAI use within their organizations.

“Based on our analysis of the ways people manipulate GenAI, and the relatively low barrier to entry to exploitation, we believe it’s imperative that organizations implement security controls within Large Language Models and take a ‘defense in depth’ approach to GenAI,” said Kev Breen, Senior Director of Threat Intelligence at Immersive Labs and a co-author of the report. “This includes implementing security measures, such as data loss prevention checks, strict input validation and context-aware filtering to prevent and recognize attempts to manipulate GenAI output.”

Key Findings from Immersive Labs “Dark Side of GenAI” Study

The team observed the following key takeaways based on their data analysis, including:

  • GenAI is no match for human ingenuity (yet): Users successfully leverage creative techniques to deceive GenAI bots, such as tricking them into embedding secrets in poems or stories or altering their initial instructions, to gain unauthorized access to sensitive information.
  • You don’t need to be an expert to exploit GenAI: The report’s findings show that even non-cybersecurity professionals and those unfamiliar with prompt injection attacks can leverage their creativity to trick bots, indicating that the barrier to exploiting GenAI in the wild using prompt injection attacks may be easier than one would hope.
  • As long as bots can be outsmarted by people, organizations are at risk: No protocols exist today to fully prevent prompt injection attacks. Cyber leaders and GenAI developers need to urgently prepare for – and respond to – this emerging threat to mitigate potential harm to people, organizations, and society.

“Our research demonstrates the critical importance of adopting a ‘secure-by-design’ approach throughout the entire GenAI system development life cycle,” added Breen. “The potential reputational harm to organizations is clear, based on examples like the ones in our report. Organizations should consider the trade-off between security and user experience, and the type of conversational model used as part of their risk assessment of using GenAI in their products and services.”

The research team at Immersive Labs consisting of Dr. John Blythe, Director of Cyber Psychology; Kev Breen, Senior Director of Cyber Threat Intelligence; and Joel Iqbal, Data Analyst, analyzed the results of Immersive Labs’ prompt injection GenAI Challenge that ran from June to September 2023. The challenge required individuals to trick a GenAI bot into revealing a secret password with increasing difficulty at each of 10 levels. The initial sample consisted of 316,637 submissions, with 34,555 participants in total completing the entire challenge. The team examined the various prompting techniques employed, user interactions, prompt sentiment, and outcomes to inform its study.

For more about these and other insights, access the report today at: https://www.immersivelabs.com/dark-side-of-genai-report/.

Featured

  • Maximizing Your Security Budget This Year

    The Importance of Proactive Security Measures: 4 Stories of Regret

    We all want to believe that crime won’t happen to us. So, some business owners hope for the best and put proactive security measures on the back burner, because other things like growth, attracting new customers, and meeting deadlines all seem more pressing. Read Now

  • New Uses for AI

    New applications of AI in IP cameras are delivering precise detection, robust search capabilities, elevated data analysis and enhanced image quality. When combined with built-in analytics, AI can help streamline forensic investigations and also supports several mission-critical business functions. Read Now

  • The Critical Missing Piece

    As technology advances, security programs have invested heavily in advanced systems and sensors. These sensors generate massive amounts of data, often overwhelming the security teams tasked with monitoring them. AI technology promises to sift through this data, using logic and reasoning to differentiate potential threats from non-threats. Read Now

  • Computers Beginning to Come Back Online After CrowdStrike Caused Crash Friday

    Computers around the world are beginning to come back online after a defective update to Windows machines from cybersecurity provider CrowdStrike Friday affected almost 9 million machines. Read Now

Featured Cybersecurity

Webinars

New Products

  • ResponderLink

    ResponderLink

    Shooter Detection Systems (SDS), an Alarm.com company and a global leader in gunshot detection solutions, has introduced ResponderLink, a groundbreaking new 911 notification service for gunshot events. ResponderLink completes the circle from detection to 911 notification to first responder awareness, giving law enforcement enhanced situational intelligence they urgently need to save lives. Integrating SDS’s proven gunshot detection system with Noonlight’s SendPolice platform, ResponderLink is the first solution to automatically deliver real-time gunshot detection data to 911 call centers and first responders. When shots are detected, the 911 dispatching center, also known as the Public Safety Answering Point or PSAP, is contacted based on the gunfire location, enabling faster initiation of life-saving emergency protocols. 3

  • Automatic Systems V07

    Automatic Systems V07

    Automatic Systems, an industry-leading manufacturer of pedestrian and vehicle secure entrance control access systems, is pleased to announce the release of its groundbreaking V07 software. The V07 software update is designed specifically to address cybersecurity concerns and will ensure the integrity and confidentiality of Automatic Systems applications. With the new V07 software, updates will be delivered by means of an encrypted file. 3

  • Connect ONE’s powerful cloud-hosted management platform provides the means to tailor lockdowns and emergency mass notifications throughout a facility – while simultaneously alerting occupants to hazards or next steps, like evacuation.

    Connect ONE®

    Connect ONE’s powerful cloud-hosted management platform provides the means to tailor lockdowns and emergency mass notifications throughout a facility – while simultaneously alerting occupants to hazards or next steps, like evacuation. 3