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

  • Tradeshow Work Can Be Fun

    While at ISC West last week, I ran into numerous friends and associates all of which was a pleasant experience. The first question always seemed to be, “How many does this make for you?” Read Now

    • Industry Events
    • ISC West
  • New Report Says 1 in 5 SMBs Would Be Forced to Shutter After Successful Cyberattack

    Small and medium-sized businesses (SMBs) play a crucial role in the U.S. economy, making up 99.9% of all businesses and contributing to half of the nation's GDP. However, these vital economic growth drivers face an escalating threat—cyberattacks that could put them out of business. Read Now

  • The Yellow Brick Road

    The road to and throughout Wednesday's and Thursday's ISC West was crowded but it was amazing. Read Now

    • Industry Events
    • ISC West
  • An Inside Look From Napco at ISC West

    Get a look into the excitement at ISC West 2025 from Napco. Hear from some of their top-tech executives live from the show floor. Read Now

    • Industry Events
    • ISC West
  • Upping the Ante

    I am not a betting man in terms of cards, dice, blackjack or that wheel with the black marble racing around the circumference of a spinning wheel, but I would bet on the success of ISC West this year. Read Now

    • Industry Events
    • ISC West

New Products

  • Camden CV-7600 High Security Card Readers

    Camden CV-7600 High Security Card Readers

    Camden Door Controls has relaunched its CV-7600 card readers in response to growing market demand for a more secure alternative to standard proximity credentials that can be easily cloned. CV-7600 readers support MIFARE DESFire EV1 & EV2 encryption technology credentials, making them virtually clone-proof and highly secure.

  • PE80 Series

    PE80 Series by SARGENT / ED4000/PED5000 Series by Corbin Russwin

    ASSA ABLOY, a global leader in access solutions, has announced the launch of two next generation exit devices from long-standing leaders in the premium exit device market: the PE80 Series by SARGENT and the PED4000/PED5000 Series by Corbin Russwin. These new exit devices boast industry-first features that are specifically designed to provide enhanced safety, security and convenience, setting new standards for exit solutions. The SARGENT PE80 and Corbin Russwin PED4000/PED5000 Series exit devices are engineered to meet the ever-evolving needs of modern buildings. Featuring the high strength, security and durability that ASSA ABLOY is known for, the new exit devices deliver several innovative, industry-first features in addition to elegant design finishes for every opening.

  • 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.