7 accepted papers
Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe actions by enforcing confidentiality and integrity policies, but currently appear costly: they reduce task completion rates…
How much information about training samples can be leaked through synthetic data generated by Large Language Models (LLMs)? Overlooking the subtleties of information flow in synthetic data generation pipelines can lead to a false sense of privacy. In this paper, we assume an adversary has access to…
Federated learning enables training high-utility models across several clients without directly sharing their private data. As a downside, the federated setting makes the model vulnerable to various adversarial attacks in the presence of malicious clients. Despite the theoretical and empirical succe…
Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, because these guarantees hold with respect to unrealistic adversaries, the protection afforded against practical attacks is typically much better. An emerging strand of work…
In the domain generalization literature, a common objective is to learn representations independent of the domain after conditioning on the class label. We show that this objective is not sufficient: there exist counter-examples where a model fails to generalize to unseen domains even after satisfyi…
Model extraction attacks attempt to replicate a target machine learning model by querying its inference API. State-of-the-art attacks are learning-based and construct replicas by supervised training on the target model’s predictions, but an emerging class of attacks exploit algebraic properties to o…
Machine learning models, especially deep neural networks are known to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used to train a model. Such privacy risks are exacerbated when a model is used for predictions on an unseen data…