October 28, 2024 at 03:58PM A new prompt-injection technique demonstrates vulnerabilities in OpenAI’s GPT-4o, allowing users to bypass its safety guardrails. By encoding malicious instructions in unconventional formats, bad actors can manipulate the model to create exploit code. The model’s inability to analyze context and prevent harmful outputs raises concerns about security in AI development. … Read more
October 17, 2024 at 01:03PM The rapid adoption of AI and machine learning raises concerns about zero-day vulnerabilities, unique to these technologies. Traditional security practices must adapt to address AI-specific threats, such as prompt injection and data leakage. Security teams are urged to integrate security throughout the AI lifecycle and conduct proactive audits to mitigate … Read more
October 16, 2024 at 08:04AM Dane Stuckey, former Chief Information Security Officer at Palantir, has joined OpenAI to lead its cybersecurity initiatives. His experience aims to enhance OpenAI’s security measures as the organization continues to develop its technologies. **Meeting Takeaways:** 1. **New Appointment**: Dane Stuckey has been appointed as the Chief Information Security Officer (CISO) … Read more
October 14, 2024 at 12:56PM Researchers from the University of Texas discovered the “ConfusedPilot” attack, which targets retrieval augmented generation (RAG)-based AI systems by introducing malicious documents. This manipulation can confuse AI responses, leading to misinformation. Current mitigation strategies include strict data access controls, integrity audits, and data segmentation to protect organizational information. **Meeting Takeaways: … Read more
October 10, 2024 at 03:54AM October marks Cybersecurity Awareness Month, emphasizing collaboration between sectors to raise cybersecurity awareness. The SANS AI Toolkit, launching this month, provides resources to help organizations use AI safely. It includes an Acceptable Use Policy and guidelines for users to maximize AI benefits while managing potential vulnerabilities. ### Meeting Notes Takeaways: … Read more
October 2, 2024 at 03:46AM Webinar by Nutanix on October 2nd at 12PM ET will focus on protecting private intellectual property (IP) in AI ecosystems, addressing challenges related to AI deployment, preventing IP exposure, and managing AI model security in cloud environments. The session is targeted at IT leaders and AI developers to balance innovation … Read more
September 26, 2024 at 10:43AM Webinar by Nutanix on October 2nd will focus on safeguarding intellectual property while using AI systems. Topics include mitigating risks in AI deployments, preventing data leakage, and managing AI model updates. It is valuable for IT leaders, security professionals, and AI developers. Register to learn how to protect your organization’s … Read more
September 17, 2024 at 10:21AM The security landscape faces an unknown challenge: adversarial use of AI. BlackBerry’s whitepaper delves into AI and its threat, including deepfakes, gen-AI malware, and phishing. The paper stresses the need for effective AI detection and prevention systems to counter the evolving AI threats and the urgency of global, societal solutions. … Read more
September 11, 2024 at 11:24AM SplxAI, an early-stage startup, has secured $2 million in pre-seed funding led by Inovo.vc, with additional investments from Runtime Ventures, South Central Ventures, and angel investors. Founded in 2023, SplxAI aims to provide a security platform to identify vulnerabilities in AI chatbots and conversational systems, with plans to build an … Read more
September 4, 2024 at 06:22PM Palo Alto Networks spends $500 million to acquire IBM’s QRadar SaaS service, aiming for a customer share. IBM assures a seamless migration to PAN’s Cortex system for eligible customers. The partnership will focus on advanced threat protection, response, and security operations using Cortex XSIAM and watsonx. IBM will continue investing … Read more