Om denne podcast
Bringing you cutting edge AI Security research
www.aiblade.net
Episoder
De nyeste 20 af 21 episoder
- Jailbreaking Grok 3 | DeepSeek, ChatGPT, Claude & More · 11 min.Article - https://www.aiblade.net/p/4030b68a-2ab6-452e-9a67-530f91a801f9 Notion Free Trial - https://affiliate.notion.so/pqesm7yjddbc AI Jailbreaking has been around since the…
- Is Github Copilot Poisoned? Part 2 · 15 min.Article - https://www.aiblade.net/p/is-github-copilot-poisoned-part-2 In my previous post, I looked at how code generation models could potentially be poisoned. The impacts could…
- How Secure Is DeepSeek? · 10 min.Article - https://www.aiblade.net/p/a2b8dbe2-ff30-4dd5-9c60-2781f07fea9a DeepSeek AI is taking the world by storm; their new R1 model provides ChatGPT-like capabilities at a…
- Is Github Copilot Poisoned? · 9 min.In my last post, I looked at the feasibility of poisoning AI models. While the task would be challenging, the payoff would be huge, allowing threat actors to inject critical…
- AI Poisoning - Is It Really A Threat? · 10 min.Article - https://www.aiblade.net/p/ai-poisoning-is-it-really-a-threat AI Training Data Poisoning is a hot topic, with OWASP citing it as the third most critical security risk…
- AI Pentesting With VulnHuntr · 6 min.Article - https://www.aiblade.net/p/ai-pentesting-with-vulnhuntr For years, CISOs have been fantasizing about truly automated penetration testing, allowing them to quickly find…
- AI Bug Bounty Guide 2024 · 9 min.Article: https://www.aiblade.net/p/ai-bug-bounty-guide-2024 Bug Bounty has long been an established source of income in the cybersecurity industry. As insecure AI/ML-based…
- Claude Computer Use - The First Prompt Injection · 7 min.Article: https://www.aiblade.net/p/claude-computer-use-prompt-injection On 22nd October 2024, Claude Computer Use was released to the world. While Computer Use is an incredible…
- Hacking The AI Goat · 9 min.Article: https://www.aiblade.net/p/hacking-the-ai-goat The AI Goat is a deliberately vulnerable AI architecture hosted on AWS. Created by Orca Security, it serves as a resource…
- Indirect Prompt Injection Methodology (IPIM) · 14 min.After exploiting several Indirect Prompt Injection vulnerabilities, I decided to author my first white paper: The Practical Application of Indirect Prompt Injection Attacks. In…
- 2024 - State of AI Security Report · 11 min.Generative AI now features in the production environments of several large organizations, yet very little research has been done surrounding its security. Orca Security seeks to…
- AI Security With Chester Wisniewski · 29 min.Chester Wisniewski is the Global Field CTO at Sophos, with a wealth of technical knowledge and over 25 years of experience in the cybersecurity industry. In this episode, we sit…
- ChatGPT - Delete My Code Without Me Asking! · 13 min.Article - https://www.aiblade.net/p/chatgpt-delete-my-code AskTheCode is a GPT that allows users to “Provide a GitHub repository URL and ask about any aspect of the code”. With…
- How Secure Will Apple Intelligence Be? · 12 min.Article: https://www.aiblade.net/p/how-secure-will-apple-intelligence-be On 10/06/24, Apple announced its long-awaited “Apple Intelligence” to the world. Apple Intelligence is a…
- ChatGPT - Send Me Someone's Calendar! · 15 min.Article: https://www.aiblade.net/p/chatgpt-send-me-someones-calendar OpenAI recently introduced GPTs to premium users, allowing people to interact with third-party web services…
- How Hugging Face Was (Ethically) Hacked · 13 min.Article: https://www.aiblade.net/p/how-hugging-face-was-ethically-hacked In this episode, we will look at how security researchers at Wiz were able to achieve Remote Code…
- AI Phone Scams: Automated Social Engineering · 17 min.Article: https://www.aiblade.net/p/ai-phone-scams Several companies have begun offering free AI phone call services, featuring large language models linked to AI voice…
- Backdoors in ML - The Dark Side of Hugging Face · 10 min.Article: https://www.aiblade.net/p/backdoors-in-ml New machine learning models are an exciting field to research. Hugging Face is the leader in this space, allowing people to…
- Unjailbreakable Large Language Models · 20 min.Article: https://www.aiblade.net/p/unjailbreakable-large-language-models Since the beginning of the AI gold rush, people have used large language models for malicious intent…
- How AI Threatens Critical Infrastructure · 10 min.Article: https://www.aiblade.net/p/how-ai-threatens-critical-infrastructure On April 26th, 2024, the Department of Homeland Security released a 28-page document outlining AI…
