Black Hat | Def Con 2024
Are you attending Black Hat? Meet the Cobalt team and Core at booth #2913!
Black Hat | Def Con 2024
Are you attending Black Hat? Meet the Cobalt team and Core at booth #2913!

LLM Security

AI Advancements and Their Impact on Cybersecurity Trends cover image

AI Advancements and Their Impact on Cybersecurity Trends

According to the State of Pentesting Report 2024, a vast majority (86%) of respondents say they have seen a significant...
LLM Security
Jun 4, 2024
Est Read Time: 6 min
Read more
The Security Risks of LLM-Powered Chatbots cover image

The Security Risks of LLM-Powered Chatbots

A large language model (LLM) is a system that draws information from large databases and uses artificial intelligence...
LLM Security
May 28, 2024
Est Read Time: 5 min
Read more
LLM Vulnerability: Excessive Agency Overview

LLM Vulnerability: Excessive Agency Overview

From prompt injection attacks to over reliance on model output correctness, large language models (LLMs) offer security...
LLM Security
Apr 30, 2024
Est Read Time: 4 min
Read more
LLM Theft prevention strategies

Large Language Model (LLM) Theft: Strategies for Prevention

Large Language Models (LLMs) process and generate human-like text, enabling applications in natural language...
LLM Security
Mar 15, 2024
Est Read Time: 7 min
Read more
LLM Insecure Output Handling cover image

LLM Insecure Output Handling

Large Language Models (LLMs), such as GPT-4, Gemini, and Mistral have become indispensable for powering everything from...
LLM Security
Mar 12, 2024
Est Read Time: 7 min
Read more
Multi-Modal Prompt Injection Attacks Using Images

Multi-Modal Prompt Injection Attacks Using Images

Recent developments have unveiled a new class of cyber threats aimed at Large Language Models (LLMs) like ChatGPT:...
LLM Security
Dec 29, 2023
Est Read Time: 4 min
Read more
Backdoor Attacks on AI Models cover image

Backdoor Attacks on AI Models

Backdoor attacks in AI and ML are a significant concern for cybersecurity experts.
LLM Security
Dec 20, 2023
Est Read Time: 5 min
Read more
Data Poisoning Attacks: A New Attack Vector within AI cover image

Data Poisoning Attacks: A New Attack Vector within AI

New types of malicious attacks involving AI systems are emerging alongside this new technology. One way for attackers...
LLM Security
Jul 26, 2023
Est Read Time: 5 min
Read more
Prompt Injection Attacks: A New Frontier in Cybersecurity cover image

Prompt Injection Attacks: A New Frontier in Cybersecurity

Prompt injection attacks have emerged as a new vulnerability impacting AI models. Specifically, large-language models...
LLM Security
May 31, 2023
Est Read Time: 8 min
Read more