All Stories
April 2023
-
How AI can improve digital security
AI-Powered Security: 7 Google Products Enhancing Protection
-
Unpacking AI Safety
Tackling AI Safety & Alignment Challenges Amid Rapid Progress and Potential Disruptions.
March 2023
-
Codex (and GPT-4) can’t beat humans on smart contract audits
GPT's Potential in Smart Contract Auditing: Current Limitations and Future Optimism as AI Capabilities Rapidly Improve.
-
To ban or not to ban: Data privacy concerns around ChatGPT and other AI
What is your organisation doing to control the potential downside of services like ChatGPT, whilst capturing the upside?
-
Cyber Insurance providers asking about company use of AI
Insurance Companies Eye AI Risks: The Need for Employee AI Policies and Guardrails in Cybersecurity Management.
-
Debunking the risk of GPU Card theft
Debunking AI Model Theft Myths: Understanding Confidential Computing & Security Engineering in Modern GPUs.
-
How to Backdoor Diffusion Models?
BadDiffusion Attack: Exposing Vulnerabilities in Image Generation AI Models and Exploring Risk Mitigation Techniques.
-
Do loose prompts sink ships?
AI-Assisted Cyberattacks: LLMs as Double-Edged Swords in Network Intrusions - Risks, Opportunities, and Detection Strategies.
-
OpenAI GPT-4 System Card
OpenAI published a 60-page System Card, a document that describes their due diligence and risk management efforts
-
Learn how hackers bypass GPT-4 controls with the first jailbreak
Can an AI be kept in its box?
Page 6 of 11