Researchers from the University of North Carolina, Chapel Hill, recently published pre-print research outlining the difficulties in deleting information from LLMs and developing mitigation methods to prevent adversarial prompting attacks.

Including security concerns at the beginning of any generative AI adoption discussion is key, but meanwhile the good news is cybersecurity budgets for AI are rising.

As adoption grows, we are seeing many applications integrated with LLMs (such as Open AI). This post helps Pentesters get started in testing LLM apps.

OpenAI GPT-3.5 Turbo chatbot defenses dissolve with '20 cents' of API tickling

In February 2023, Microsoft disclosed its new AI-assisted search engine, Bing Chat, powered by OpenAI’s GPT-4. Even though Google has been...

GPT4-V is the new mode of GPT-4 that allows you to upload images as part of your conversations. It’s absolutely brilliant. It also provides a whole new set of vectors …

North Korea is escalating its cyber capabilities by harnessing the power of artificial intelligence (AI), according to Deputy National Security Advisor Anne Neuberger.

NCC Group report claims machine learning models show strong promise in detecting novel zero-day attacks.

As the US and China meet for the APEC summit in San Francisco this week, American officials are pushing for talks on the risks posed by military use of AI.

ChatGPT and large language models are the early signs of how generative AI will shape many business processes. Security and risk management leaders, specifically CISOs, and their teams need to secure how their organization builds and consumes generative AI, and navigate its impacts on cybersecurity.

Dubbed LoveGPT by researchers at Avast, the tool can get around dating apps' security measures, send likes, read replies from potential matches and create believable profiles.

AI systems are used increasingly in various applications, including autonomous vehicles, medical diagnostics, and biometric authentication…

What impact will generative AI have on cybersecurity — and how will its evolution affect business decisions going forward? C-suite leaders weigh in.

The tool, called Nightshade, messes up training data in ways that could cause serious damage to image-generating AI models. 

There is no shortage of researchers and industry titans willing to warn us about the potential destructive power of artificial intelligence. Reading the headlines, one would hope that the rapid gains in AI technology have also brought forth a unifying realization of the risks—and the steps we need to take to mitigate them.

Indemnity clauses vary widely between generative AI vendors -- and there's no sign of convergence or consensus on the horizon.

Leveraging AI, cloud-native technology, and unified data to empower security teams with the speed required to defend against accelerated cyberthreats.

This repository contains scripts and related documentation that demonstrate attacks against large language models using repeated character sequences. These techniques can be used to execute prompt injection on content-constrained LLM queries.