Security threat modelling is a passion of mine and I believe this it is an excellent method to identify potential security risks and target our limited resources towards possible likely attacks towards the systems we are protecting. Ever since OpenAI released ChatGPT I have been playing around with

Rapid growth of generative AI-based software is challenging business technology leaders to keep potential cybersecurity issues in check.

The AI model trained on typing recorded over a smartphone was able to steal passwords with 95% accuracy.

Despite increased digitization over the last decade, most organizations continue to rely on signatures as the primary method of transaction authentication.

"The bar has been raised for both attackers and defenders. No one will ultimately emerge victorious; it will remain a cat-and-mouse game. Education is valuable, but technology is the solution," says Team8 Chief Innovation Officer Bobi Gilburd

The emergence of artificial intelligence (AI) has given rise to a troubling new type of fraud that i...

A world where the evidence itself becomes a suspect.

Explore how information retrieval systems may be used to perpetrate prompt injection attacks and how application developers can mitigate this risk.

Cybersecurity experts have incorporated ChatGPT-like tools into their work, and they use them for tasks from source-code analysis to identifying vulnerabilities.

Microsoft established the AI Red Team: a group of interdisciplinary experts dedicated to thinking like attackers and probing AI systems for failures.

White House officials concerned by AI chatbots' potential for societal harm.

An open-source, extensible knowledge base of AI failures

The starting point for information about the AI Incident Database

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Protect AI is proud to announce the acquisition of 418Sec, a cybersecurity research community, and their bug bounty platform, huntr! With this acquisition comes the launch of the world's first artificial intelligence and machine learning bug bounty platform. We’d like to congratulate and welcome to

MITRE ATLAS™ (Adversarial Threat Landscape for Artificial-Intelligence Systems), is a knowledge base of adversary tactics, techniques, and case studies for machine learning (ML) systems based on real-world observations

An extension for Burp Suite to allow researchers to utilize GPT for analys is of HTTP requests and responses - GitHub - tenable/Burp-extension-for-GPT: an extension for Burp Suite to allow research...

A comprehensive and up-to-date database to manage and mitigate the risks associated with AI systems.

Generative AI is emerging as a top concern for organizations. Here's what they're doing about it.

Delve into the critical topic of data-driven AI. Explore the risks and mitigation strategies that arise from its data-centric nature.

Exclusive: FOI document reveals staff could not recall what they entered into AI chatbot and Greens senator says lack of safety protocols raises questions

The 24 guidelines include measures that touch on user privacy, data sourcing, content labeling, security reviews and government approval.

Several leading AI companies – Anthropic, Google, Microsoft, and OpenAI – to partner with DARPA in major competition to make software more secure The Biden-Harris Administration today launched a major two-year competition that will use artificial intelligence (AI) to protect the United States’ most important software, such as code that helps run the internet and…

The industry-first solution empowers security operations centers (SOCs) to harness the power of AI to boost security analyst productivity, detect more real attacks, and greatly reduce incident remediation times.

Chen Burshan, CEO of cloud security vendor Skyhawk Security, explains how ChatGPT can help secure the cloud. Read on to learn more.

Vicarius released vuln_GPT, a Generative AI for cyber security that auto-generates remediation scripts for software vulnerabilities. This tool is designed to counter threats faster than hackers can exploit them.

LLM Prompt Injection Detector. Contribute to protectai/rebuff development by creating an account on GitHub.

This paper focuses on the impact of leveraging autonomous offensive approaches in Deep Reinforcement Learning (DRL) to train more robust agents by exploring the impact of applying adversarial learning to DRL for autonomous security in Software Defined Networks (SDN).