You can try our interactive demo! (Or read our preprint.)
Here, we want to explain why we care about this work from an AI safety perspective.
Concerning Properties of Image Hijacks
What are image hijacks?
To the best of our knowledge, image hijacks constitute the first demonstration of adversarial inputs for foundation models that
- force the model to perform some arbitrary behaviour (e.g. "output the string Visit this website at malware.com!"),
- while being barely distinguishable from a benign input,
- and automatically synthesisable given a dataset of examples of .
It's possible that a future text-only attack could do these things, but such an attack hasn't yet been demonstrated.
Why should we care?
We expect that future (foundation-model-based) AI systems will be able to
- consume unfiltered data from the Internet (e.g. searching the Web),
- access sensitive personal information (e.g. a user's email history), and
- take actions in the world on behalf of a user (e.g. sending emails, downloading files, making purchases, executing code).
As the actions of such foundation-model-based agents are based on the foundation model's text output, hijacking the foundation model's text output could give an adversary arbitrary control over the agent's behaviour.
Relevant AI Safety Projects
Race to the top on adversarial robustness. Robustness to attacks such as image hijacks is (i) a control problem, (ii) which we can measure, and (iii) which has real-world safety implications today. So we're excited to see AI labs compete to have the most adversarially robust models.
Third-party auditing and certification. Auditors could test for robustness against image hijacks, both at the foundation model level (auditing the major AGI corporations) and at the app development level (auditing downstream companies integrating foundation models into their products). Image hijacks could also be used to test for the presence of dangerous capabilities (characterisable as some behaviour ) by attempting to train an image hijack for that capability.
Liability for AI-caused harms, penalizing externalities. Both the Future of Life Institute and Jaan Tallinn advocate for liability for AI-caused harms. When assessing AI-caused harms, image hijacks may need to be part of the picture.
I think this is an interesting point. We are actually conducting some follow-up work seeing how robust our attacks are to various additional "defensive" perturbations (e.g. downscaling, adding noise). As Matt notes, when doing these experiments it is important to see how such perturbations also affect the models general vision language modeling performance. My prior right now is that using this technique it may be possible to defend against the L infinity constrained images, but possibly not the moving patch attacks that showed higher level features. In general adversarial attacks are a cat and mouse game, so I expect that if we can show you can defend using techniques like this, a new training scheme will come along that is able to make adversaries that are robust to such defenses. It is worth noting also that most VLMs only accept small low resolution images already. For example LLaVA (with llama 13b), which is state of the art for open source, only accepts ~200 * 200 pixel sized image, so the above example is not necessarily a fair one.