90 citations · 331 across the 28 of their papers we have counts for
29 papers
SPIDES: Information-Flow Control for Browser Agents
Egor Zverev, Juhee Kim, Leon Trampert +4
Browser agents automate complex workflows by reading and acting on arbitrary page content, but this flexibility exposes them to prompt injection attacks and unintended data exfiltr…
Optimizing Agent Planning for Security and Autonomy
Aashish Kolluri, Rishi Sharma, Manuel Costa +5
Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe act…
Securing AI Agents with Information-Flow Control
Manuel Costa, Boris Köpf, Aashish Kolluri +6
As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of i…
The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
Matthieu Meeus, Lukas Wutschitz, Santiago Zanella-Béguelin +2
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 synthe…
Permissive Information-Flow Analysis for Large Language Models
Shoaib Ahmed Siddiqui, Radhika Gaonkar, Boris Köpf +7
Large Language Models (LLMs) are rapidly becoming commodity components of larger software systems. This poses natural security and privacy problems: poisoned data retrieved from on…
Closed-Form Bounds for DP-SGD against Record-level Inference
Giovanni Cherubin, Boris Köpf, Andrew Paverd +3
Machine learning models trained with differentially-private (DP) algorithms such as DP-SGD enjoy resilience against a wide range of privacy attacks. Although it is possible to deri…
Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective
Lukas Wutschitz, Boris Köpf, Andrew Paverd +6
Modern machine learning systems use models trained on ever-growing corpora. Typically, metadata such as ownership, access control, or licensing information is ignored during traini…
SoK: Memorization in General-Purpose Large Language Models
Valentin Hartmann, Anshuman Suri, Vincent Bindschaedler +3
Large Language Models (LLMs) are advancing at a remarkable pace, with myriad applications under development. Unlike most earlier machine learning models, they are no longer built f…
Why Train More? Effective and Efficient Membership Inference via Memorization
Jihye Choi, Shruti Tople, Varun Chandrasekaran +1
Membership Inference Attacks (MIAs) aim to identify specific data samples within the private training dataset of machine learning models, leading to serious privacy violations and…
Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting
Ana-Maria Cretu, Daniel Jones, Yves-Alexandre de Montjoye +1
Machine learning models have been shown to leak sensitive information about their training datasets. Models are increasingly deployed on devices, raising concerns that white-box ac…
On the Efficacy of Differentially Private Few-shot Image Classification
Marlon Tobaben, Aliaksandra Shysheya, John Bronskill +5
There has been significant recent progress in training differentially private (DP) models which achieve accuracy that approaches the best non-private models. These DP models are ty…
Analyzing Leakage of Personally Identifiable Information in Language Models
Nils Lukas, Ahmed Salem, Robert Sim +3
Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs…
SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
Ahmed Salem, Giovanni Cherubin, David Evans +5
Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of in…
Membership Inference Attacks and Generalization: A Causal Perspective
Teodora Baluta, Shiqi Shen, S. Hitarth +2
Membership inference (MI) attacks highlight a privacy weakness in present stochastic training methods for neural networks. It is not well understood, however, why they arise. Are t…
Invariant Aggregator for Defending against Federated Backdoor Attacks
Xiaoyang Wang, Dimitrios Dimitriadis, Sanmi Koyejo +1
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 vul…
Distribution inference risks: Identifying and mitigating sources of leakage
Valentin Hartmann, Léo Meynent, Maxime Peyrard +3
A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inferen…
Bayesian Estimation of Differential Privacy
Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople +6
Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that su…
The Connection between Out-of-Distribution Generalization and Privacy of ML Models
Divyat Mahajan, Shruti Tople, Amit Sharma
With the goal of generalizing to out-of-distribution (OOD) data, recent domain generalization methods aim to learn "stable" feature representations whose effect on the output remai…
Causally Constrained Data Synthesis for Private Data Release
Varun Chandrasekaran, Darren Edge, Somesh Jha +3
Making evidence based decisions requires data. However for real-world applications, the privacy of data is critical. Using synthetic data which reflects certain statistical propert…
MACE: A Flexible Framework for Membership Privacy Estimation in Generative Models
Yixi Xu, Sumit Mukherjee, Xiyang Liu +3
Generative machine learning models are being increasingly viewed as a way to share sensitive data between institutions. While there has been work on developing differentially priva…
SOTERIA: In Search of Efficient Neural Networks for Private Inference
Anshul Aggarwal, Trevor E. Carlson, Reza Shokri +1
ML-as-a-service is gaining popularity where a cloud server hosts a trained model and offers prediction (inference) service to users. In this setting, our objective is to protect th…
Domain Generalization using Causal Matching
Divyat Mahajan, Shruti Tople, Amit Sharma
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…
Leakage of Dataset Properties in Multi-Party Machine Learning
Wanrong Zhang, Shruti Tople, Olga Ohrimenko
Secure multi-party machine learning allows several parties to build a model on their pooled data to increase utility while not explicitly sharing data with each other. We show that…
FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning
Sameer Wagh, Shruti Tople, Fabrice Benhamouda +3
We propose Falcon, an end-to-end 3-party protocol for efficient private training and inference of large machine learning models. Falcon presents four main advantages - (i) It is hi…