Tag
5 articles
Security researcher Aonan Guan exploited prompt injection flaws in AI agents from Anthropic, Google, and Microsoft, stealing API keys. All three companies paid bug bounties but did not issue public advisories.
OpenAI reveals new defenses against prompt injection attacks and social engineering in ChatGPT, strengthening AI agent security through constrained workflows and enhanced data protection.
OpenAI has released IH-Challenge, a training dataset designed to teach AI models to reliably prioritize trusted instructions over untrusted ones, improving security and defense against prompt injection attacks.
OpenAI introduces IH-Challenge, a training method that improves instruction hierarchy in frontier LLMs, enhancing safety steerability and resistance to prompt injection attacks.
Learn to implement Lockdown Mode and Elevated Risk labels in AI chat interfaces to defend against prompt injection attacks and data exfiltration, similar to OpenAI's new security features.
