Secure AI Weekly

AI safety guardrails easily thwarted, security study finds The Register, October 12, 2023 Models, such as OpenAI’s GPT-3.5 Turbo, were designed with built-in safety measures to prevent the generation of harmful or toxic content. However, recent research has shed light on the vulnerability of these safeguards, revealing that they may ...

Dead grandma locket request tricks Bing Chat’s AI into solving security puzzle ArsTechnica, October 2, 2023 Microsoft’s Bing Chat designed similarly to ChatGPT, allows users to share images for the AI to assess. Notably, it’s programmed to resist solving CAPTCHAs, those visual tests aimed at thwarting bots on the web. ...

Malicious Actors Exploiting AI Chatbot Jailbreaking Tips Security Boulevard, September 27, 2023 Recent developments in the world of AI have raised concerns about the security and safety of these advanced systems. Malicious actors have been collaborating to breach the ethical and safety boundaries placed around AI chatbots like ChatGPT. This ...

OpenAI Red Teaming Network OpenAI, September 19, 2023 Finally, OpenAI launched the OpenAI Red Teaming Network, a pivotal initiative designed to bolster the safety and security of our AI models. This venture welcomes experts from a myriad of fields to collaborate, utilizing their diverse insights for the thorough evaluation and ...

Comply or Die: The Rise of the AI Governance Stack Battery Ventures, September 13, 2023 While regulatory efforts are catching up, with the European Union leading the way and localized efforts in the United States filling the federal void, there is still much work to be done. As the race ...

Tackling Trust, Risk and Security in AI Models Gartner, September 5, 2023 The surge of interest in generative AI technologies has led to a plethora of pilot projects, but what often falls by the wayside is a robust risk assessment. Organizations frequently don’t consider safety and security implications until their ...

UK cybersecurity agency warns of chatbot ‘prompt injection’ attacks The Guardian, August 30, 2023 The United Kingdom’s National Cyber Security Centre (NCSC) has recently raised alarms about the escalating cybersecurity threats surrounding chatbots. These automated conversational agents, powered by large language models (LLMs) like OpenAI’s ChatGPT and Google’s Bard, are ...

Tricks for making AI chatbots break rules are freely available online NewScientist, August 21, 2023 Artificial intelligence chatbots like ChatGPT have become essential tools for various online activities, but their security loopholes present an emerging concern. Manipulative text prompts, often referred to as “jailbreak prompts,” can mislead these AI systems ...

Don’t expect quick fixes in ‘red-teaming’ of AI models. Security was an afterthought APNews, August 14, 2023 The recent DefCon hacker conference in Las Vegas served as a stark reminder of the pressing concerns around AI safety and security. The event saw 2,200 participants rigorously testing eight advanced language models, ...