Why every AI agent is vulnerable to attack

AI agents are rapidly moving from experimental tools to trusted decision-makers inside the enterprise—but security has not ...
eWeek

A ‘Zombie’ AI Attack Shows How ChatGPT Can Leak Your Secrets

Radware’s ZombieAgent technique shows how prompt injection in ChatGPT apps and Memory could enable stealthy data theft ...
ZDNet

How OpenAI is defending ChatGPT Atlas from attacks now - and why safety's not guaranteed

OpenAI built an "automated attacker" to test Atlas' defenses. The qualities that make agents useful also make them vulnerable. AI security will be a game of cat and mouse for a long time. OpenAI is ...
IEEE

Using ChatGPT in Designing Web Applications Resistant to SQL Injection Attacks

Abstract: This paper investigates leveraging ChatGPT as a tool for testing web applications resilient to SQL injection attacks. Subsequently, the web application analysis is conducted using different ...
IEEE

Preventing SQL Injection Attacks with Machine Learning: A TF-IDF + XGBoost Approach

Abstract: SQL injection is still one of the most exploited threats as a result of the rapid rise of web-based threats. Therefore, this paper presents a security framework for SQL injection attack ...