… From there, a key protection against prompt injection and data exfiltration attacks occurs at the URL level. With external data containing dynamic URLs, users may encounter unknown risks as these URLs may be designed for indirect prompt injections and data exfiltration attacks. …
… These optimization-based attacks are designed to be as strong as possible; weak attacks do little to inform us of the susceptibility of an AI system to indirect prompt injections. …
… In total, Guan and his fellow researchers demonstrated that attackers can use this prompt injection technique to steal Anthropic and Gemini API keys, multiple GitHub tokens, and "any other secret exposed in the GitHub Actions runner environment, including arbitrary user-defined repository or organi… …
… To learn more about Google’s progress and research on generative AI threat actors, attack techniques, and vulnerabilities, take a look at the following resources: Google Workspace’s continuous approach to mitigating indirect prompt injections blog post from Google’s GenAI security team Mitigating p… …
Interesting new research you may have heard of on attacking large audio language models. The attack is called AudioHijack and the part worth paying attention to is that adversarial clips built against open models transfe…
Hey HN! We're Dr. Kashyap Thimmaraju and Giuseppe Canale from Silicon Psyche. We've built Posture Sequence Analysis (PSA), a behavioural health monitor for LLMs and AI Agents.Why we built PSAWe built PSA because we wante…
… Honest inputs: Paragraphs sourced from random Wikipedia articles, used to simulate non-adversarial, benign-looking inputs e.g., in the context of indirect prompt injection via RAG or similar systems . …
… Staying ahead of the latest indirect prompt injection attacks is critical to our mission of securing Workspace with Gemini. In our previous blog “ Mitigating prompt injection attacks with a layered defense strategy ”, we reviewed the layered architecture of our IPI defenses. …
… A successful prompt injection attack can ripple across apps and system-level behavior at the same time. …
Papers arxiv:2604.28157 FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption Published on Apr 30 Submitted by yanting wang on May 1 Pennsylvania State University Authors: , , , Abstract FlashRT is a framework that significantly improves the… …
… "There are multiple steps involved with prompt injection attacks, and people have been doing it in a relatively manual fashion," Efstathopoulos said. …
… We call it phishing when it targets humans, and prompt injection is pretty much the same thing for bots. …