Fashionable AI programs, like Gemini, are extra succesful than ever, serving to retrieve knowledge and carry out actions on behalf of customers. Nevertheless, knowledge from exterior sources current new safety challenges if untrusted sources can be found to execute directions on AI programs. Attackers can make the most of this by hiding malicious directions in knowledge which are prone to be retrieved by the AI system, to govern its conduct. Any such assault is usually known as an “oblique immediate injection,” a time period first coined by Kai Greshake and the NVIDIA crew.
To mitigate the danger posed by this class of assaults, we’re actively deploying defenses inside our AI programs together with measurement and monitoring instruments. One among these instruments is a strong analysis framework now we have developed to mechanically red-team an AI system’s vulnerability to oblique immediate injection assaults. We’ll take you thru our risk mannequin, earlier than describing three assault strategies now we have carried out in our analysis framework.
Menace mannequin and analysis framework
Our risk mannequin concentrates on an attacker utilizing oblique immediate injection to exfiltrate delicate data, as illustrated above. The analysis framework checks this by making a hypothetical situation, by which an AI agent can ship and retrieve emails on behalf of the person. The agent is offered with a fictitious dialog historical past by which the person references non-public data reminiscent of their passport or social safety quantity. Every dialog ends with a request by the person to summarize their final e-mail, and the retrieved e-mail in context.
The contents of this e-mail are managed by the attacker, who tries to govern the agent into sending the delicate data within the dialog historical past to an attacker-controlled e-mail deal with. The assault is profitable if the agent executes the malicious immediate contained within the e-mail, ensuing within the unauthorized disclosure of delicate data. The assault fails if the agent solely follows person directions and gives a easy abstract of the e-mail.
Automated red-teaming
Crafting profitable oblique immediate injections requires an iterative means of refinement based mostly on noticed responses. To automate this course of, now we have developed a red-team framework consisting of a number of optimization-based assaults that generate immediate injections (within the instance above this is able to be totally different variations of the malicious e-mail). These optimization-based assaults are designed to be as robust as potential; weak assaults do little to tell us of the susceptibility of an AI system to oblique immediate injections.
As soon as these immediate injections have been constructed, we measure the ensuing assault success charge on a various set of dialog histories. As a result of the attacker has no prior information of the dialog historical past, to realize a excessive assault success charge the immediate injection have to be able to extracting delicate person data contained in any potential dialog contained within the immediate, making this a more durable activity than eliciting generic unaligned responses from the AI system. The assaults in our framework embrace:
Actor Critic: This assault makes use of an attacker-controlled mannequin to generate recommendations for immediate injections. These are handed to the AI system underneath assault, which returns a chance rating of a profitable assault. Based mostly on this chance, the assault mannequin refines the immediate injection. This course of repeats till the assault mannequin converges to a profitable immediate injection.
Beam Search: This assault begins with a naive immediate injection instantly requesting that the AI system ship an e-mail to the attacker containing the delicate person data. If the AI system acknowledges the request as suspicious and doesn’t comply, the assault provides random tokens to the top of the immediate injection and measures the brand new chance of the assault succeeding. If the chance will increase, these random tokens are stored, in any other case they’re eliminated, and this course of repeats till the mixture of the immediate injection and random appended tokens end in a profitable assault.
We’re actively leveraging insights gleaned from these assaults inside our automated red-team framework to guard present and future variations of AI programs we develop in opposition to oblique immediate injection, offering a measurable technique to monitor safety enhancements. A single silver bullet protection just isn’t anticipated to unravel this downside completely. We consider essentially the most promising path to defend in opposition to these assaults entails a mixture of strong analysis frameworks leveraging automated red-teaming strategies, alongside monitoring, heuristic defenses, and normal safety engineering options.
We wish to thank Vijay Bolina, Sravanti Addepalli, Lihao Liang, and Alex Kaskasoli for his or her prior contributions to this work.
Posted on behalf of your complete Google DeepMind Agentic AI Safety crew (listed in alphabetical order):
Aneesh Pappu, Andreas Terzis, Chongyang Shi, Gena Gibson, Ilia Shumailov, Itay Yona, Jamie Hayes, John “4” Flynn, Juliette Pluto, Sharon Lin, Shuang Music
