Get the latest tech news
New Hack Uses Prompt Injection To Corrupt Gemini's Long-Term Memory
An anonymous reader quotes a report from Ars Technica: On Monday, researcher Johann Rehberger demonstrated a new way to override prompt injection defenses Google developers have built into Gemini -- specifically, defenses that restrict the invocation of Google Workspace or other sensitive tools when...
The result of Rehberger's attack is the permanent planting of long-term memories that will be present in all future sessions, opening the potential for the chatbot to act on false information or instructions in perpetuity. Based on lessons learned previously, developers had already trained Gemini to resist indirect prompts instructing it to make changes to an account's long-term memories without explicit directions from the user. Google responded in a statement to Ars: "In this instance, the probability was low because it relied on phishing or otherwise tricking the user into summarizing a malicious document and then invoking the material injected by the attacker.
Or read this on Slashdot
