Best of Cybersecurity — May 2024
- 1
- 2
- 3
- 4
- 5
Community Picks·2y
LLM Agents can Autonomously Hack Websites
LLM agents have been shown to autonomously hack websites, raising questions about their potential for dual use. This post explores the capabilities of LLM agents, their ability to perform complex hacks, and the implications of their deployment.
- 6
- 7
- 8
InfoWorld·2y
10 big devops mistakes and how to avoid them
Devops continues to grow in popularity as organizations look for ways to add efficiencies to the development process. Certain mistakes can sabotage development efforts if not addressed, such as lack of communication between dev and ops teams, overlooking cybersecurity, complex IT infrastructure, misalignment of devops priorities with business goals, integration of new technologies without proper evaluation, reliance on outdated technologies, cultural resistance to change, challenges of remote work, divergent goals between dev and ops teams, and the misconception that automation solves everything.
- 9
- 10
- 11
- 12
Embrace The Red·2y
Machine Learning Attack Series: Backdooring Keras Models and How to Detect It · Embrace The Red
This post explores the threat of model deserialization issues in machine learning, specifically backdooring Keras models. It provides a step-by-step guide to detecting and mitigating backdoored model files, and recommends integrating detection tooling into MLOps pipelines.
- 13
Embrace The Red·2y
ChatGPT: Hacking Memories with Prompt Injection · Embrace The Red
OpenAI introduces a memory feature in ChatGPT that allows it to recall information across sessions. However, this feature also comes with risks, as it can be manipulated by attackers to store false memories or instructions. Three attack avenues are explored: connected apps, uploaded documents, and browsing. The post provides demonstrations and recommendations to protect interactions with AI.