PinnedSplxAIProfanity Patterns: ChatGPT’s date-linked moodinessIt has been observed that even the smallest of changes in a system prompt can influence the output to some degree. If you have a system…Jul 29Jul 29
PinnedSplxAIIKEA, ChatGPT, and the Bias DilemmaIKEA launched its ChatGPT AI assistant in February this year. You can access it if you’re a ChatGPT Plus user. The goal is to provide users…Jul 17Jul 17
SplxAIUnlocking real business value with secure GenAI applicationsA deep dive into internal and external enterprise use-cases of GenAI and the risks involvedOct 15Oct 15
SplxAIRAG Poisoning in enterprise knowledge sourcesHow AI assistants integrated with knowledge sources like Confluence can expose enterprises to data leakage risksOct 13Oct 13
SplxAIExploring Ethical AI and Content Filtering in Character.AIExamining the Challenges and Loopholes in Content Moderation for Responsible AI UseAug 15Aug 15
SplxAIVoice Prompt Injection on ChatGPTIn the ever-expanding attack surface of AI applications, new security vulnerabilities emerge all the time, and OpenAI’s new GPT-4o voice…Jun 18Jun 18
SplxAIHow to Lose Millions with Bad Guardrails: Stricter Is Not BetterGuardrails in AI systems are defensive security measures designed to keep chatbot interactions within safe and predefined boundaries…May 27May 27
SplxAIPTaaS (Penetration Testing as a Service) vs Manual Pen-testing?In today’s tech-driven world, keeping AI applications, especially chatbots, secure is a big deal. With advanced models like ChatGPT and…May 24May 24
SplxAIMeeting EU AI Act Compliance with SplxAISuccess in creating AI would be the biggest event in human history. Unfortunately, it might also be the last, unless we learn how to avoid…May 16May 16
SplxAIGoogle’s Checklist to AI Security: Don’t Let Your AI Go RogueGoogle recently unveiled its “AI Security Best Practices Checklist”.May 8May 8
