~/category/adversarial-ai
Attacks on and with AI — prompt injection, model red teaming, AI-driven offense and defense.
25 articles
My annual pilgrimage to Las Vegas for Black Hat USA and DEF CON—what many of my friends affectionately call “Hacker Summer Camp”—took place from August 2–7, 2025, at the Mandalay Bay Convention Center, with DEF CON extending the festivities through August 10 at the Las Vegas Convention Center.Last y
The first step is to update your system. Assuming you have a relatively new build of Kali and a simple apt-get update and upgrade command, it should work fine here.Before you get started I recommend switching to root by issuing the command:sudo -i Step 1:apt-get update -y && apt-get upgrade -yNext,
Artificial Intelligence (AI) has transformed how we interact with technology. Large language models (LLMs) are among the most prominent advancements, with OpenAI's ChatGPT being a well-known example. However, in specialized environments such as Linux, particularly for development, scripting, and com
Phishing continues to be the number one attack vector and impersonation attacks are not new. What is interesting is how there are threat actors using AI to enhance classic attacks.I’ve seen various versions of this attack from claims that I didn’t pay my taxes BUT I can wire money now (see more on t
Everybody is racing to develop an AI strategy, and many do not understand the risks associated with AI. Microsoft recently posted an article speaking to this concern found HERE. I found this section of the post very interesting …Recommendations for AI security strengthening:Apply vendor AI controls
The ever-expanding realm of artificial intelligence, OpenAI's GPT (Generative Pre-trained Transformer) models have consistently pushed the boundaries of what is possible in natural language processing. With the release of GPT-4.0, the latest iteration of this transformative technology, many are cur
Artificial intelligence (AI) can revolutionize cybersecurity by enabling organizations to detect, prevent, and respond to cyber threats. In this essay, we will explore how AI can enhance cybersecurity and discuss some of the challenges and considerations that need to be considered when implementing
Artificial intelligence (AI) and machine learning (ML) are often used interchangeably, but they are different. Understanding the difference between these two technologies is important, as it can help individuals and organizations make informed decisions about how they can be used to solve problems a
The Clark-Wilson security model is based on preserving information integrity against the malicious attempt of tampering with data. The security model maintains that only authorized users should make and be allowed to change the data, unauthorized users should not make any changes, and the system sho
On this week's podcast, my co-host Tony G is back! Join us as we interview Jack Chan product manager at Fortinet. Jack discusses his thoughts on how we have seen artificial intelligence and machine learning evolve in products offered by OEMs and other vendors in the last year and what benefits we ca
There are several baby monitors that have come on the market recently with remote viewing capabilities, motion detection, and temperature sensors. These are great tools that give parents peace of mind, but with the proliferation of the Internet of Things and manufactures designing products for funct
The Clark-Wilson security model is based on preserving information integrity against the malicious attempt of tampering data. The security model maintains that only authorized users should make and be allowed to change the data, unauthorized users should not be able to make any changes, and the syst